{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/method/sharpness-aware-minimization","slug":"sharpness-aware-minimization","name":"Sharpness-Aware Minimization","full_name":"Sharpness-Aware Minimization","full_name_withheld":false,"description_markdown":"**Sharpness-Aware Minimization**, or **SAM**, is a procedure that improves model generalization by simultaneously minimizing loss value and loss sharpness. SAM functions by seeking parameters that lie in neighborhoods having uniformly low loss value (rather than parameters that only themselves have low loss value).","description_state":"present","introduced_year":null,"introduced_by":{"title":"Sharpness-Aware Minimization for Efficiently Improving Generalization","paper":"/paper/sharpness-aware-minimization-for-efficiently-1","first_author":"Pierre Foret","n_authors":4,"url_abs":null,"archive_paper_url":"https://paperswithcode.com/paper/sharpness-aware-minimization-for-efficiently-1"},"source":{"url":"https://arxiv.org/abs/2010.01412v3","title":"Sharpness-Aware Minimization for Efficiently Improving Generalization","url_on_a_paper_host":true},"code_snippet_url":null,"code_snippet_url_on_a_code_host":false,"categories":[{"area":"General","area_id":"general","collection":"Optimization","url":"/methods/category/optimization","pwc_aliases":[]}],"n_papers_tagged":142,"archive_num_papers":142,"papers_newest_first":[{"paper":"/paper/samo-a-lightweight-sharpness-aware-approach","slug":"samo-a-lightweight-sharpness-aware-approach","title":"SAMO: A Lightweight Sharpness-Aware Approach for Multi-Task Optimization with Joint Global-Local Perturbation","date":"2025-07-10","arxiv_id":"2507.07883","n_code_links":1,"syntology":{"ran":0,"of":1,"n_ran_checked":0,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"0 ran · 1 unverified","official":{"repos":["OptMN-Lab/SAMO"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"paper":"/paper/sharpness-aware-machine-unlearning","slug":"sharpness-aware-machine-unlearning","title":"Sharpness-Aware Machine Unlearning","date":"2025-06-16","arxiv_id":"2506.13715","n_code_links":0,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result","official":null}},{"paper":null,"slug":"from-sharpness-to-better-generalization-for","title":"From Sharpness to Better Generalization for Speech Deepfake Detection","date":"2025-06-13","arxiv_id":"2506.11532","n_code_links":0,"syntology":null},{"paper":null,"slug":"towards-understanding-the-calibration","title":"Towards Understanding The Calibration Benefits of Sharpness-Aware Minimization","date":"2025-05-29","arxiv_id":"2505.23866","n_code_links":0,"syntology":null},{"paper":null,"slug":"an-analysis-of-concept-bottleneck-models","title":"An Analysis of Concept Bottleneck Models: Measuring, Understanding, and Mitigating the Impact of Noisy Annotations","date":"2025-05-22","arxiv_id":"2505.16705","n_code_links":0,"syntology":null},{"paper":"/paper/improving-generalization-of-medical-image","slug":"improving-generalization-of-medical-image","title":"Improving Generalization of Medical Image Registration Foundation Model","date":"2025-05-10","arxiv_id":"2505.06527","n_code_links":1,"syntology":null},{"paper":null,"slug":"learning-from-loss-landscape-generalizable","title":"Learning from Loss Landscape: Generalizable Mixed-Precision Quantization via Adaptive Sharpness-Aware Gradient Aligning","date":"2025-05-08","arxiv_id":"2505.04877","n_code_links":0,"syntology":null},{"paper":null,"slug":"focal-sam-focal-sharpness-aware-minimization","title":"Focal-SAM: Focal Sharpness-Aware Minimization for Long-Tailed Classification","date":"2025-05-03","arxiv_id":"2505.01660","n_code_links":0,"syntology":null},{"paper":null,"slug":"federated-endovit-pretraining-vision","title":"Federated EndoViT: Pretraining Vision Transformers via Federated Learning on Endoscopic Image Collections","date":"2025-04-23","arxiv_id":"2504.16612","n_code_links":0,"syntology":null},{"paper":"/paper/mitigating-parameter-interference-in-model","slug":"mitigating-parameter-interference-in-model","title":"Mitigating Parameter Interference in Model Merging via Sharpness-Aware Fine-Tuning","date":"2025-04-20","arxiv_id":"2504.14662","n_code_links":1,"syntology":{"ran":0,"of":2,"n_ran_checked":0,"n_instrument":0,"unverified":2,"pointer_only":2,"phrase":"0 ran · 2 unverified","official":{"repos":["baiklab/saft-merge"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":[]}}},{"paper":null,"slug":"dgsam-domain-generalization-via-individual","title":"DGSAM: Domain Generalization via Individual Sharpness-Aware Minimization","date":"2025-03-30","arxiv_id":"2503.23430","n_code_links":0,"syntology":null},{"paper":null,"slug":"fairsam-fair-classification-on-corrupted-data","title":"FairSAM: Fair Classification on Corrupted Data Through Sharpness-Aware Minimization","date":"2025-03-29","arxiv_id":"2503.22934","n_code_links":0,"syntology":null},{"paper":null,"slug":"the-devil-is-in-low-level-features-for-cross","title":"The Devil is in Low-Level Features for Cross-Domain Few-Shot Segmentation","date":"2025-03-27","arxiv_id":"2503.21150","n_code_links":0,"syntology":null},{"paper":null,"slug":"training-diagonal-linear-networks-with","title":"Training Diagonal Linear Networks with Stochastic Sharpness-Aware Minimization","date":"2025-03-14","arxiv_id":"2503.11891","n_code_links":0,"syntology":null},{"paper":null,"slug":"understanding-flatness-in-generative-models","title":"Understanding Flatness in Generative Models: Its Role and Benefits","date":"2025-03-14","arxiv_id":"2503.11078","n_code_links":0,"syntology":null},{"paper":null,"slug":"effective-llm-knowledge-learning-via-model","title":"Effective LLM Knowledge Learning via Model Generalization","date":"2025-03-05","arxiv_id":"2503.03705","n_code_links":0,"syntology":null},{"paper":null,"slug":"lorenza-enhancing-generalization-in-low-rank","title":"LORENZA: Enhancing Generalization in Low-Rank Gradient LLM Training via Efficient Zeroth-Order Adaptive SAM","date":"2025-02-26","arxiv_id":"2502.19571","n_code_links":0,"syntology":null},{"paper":null,"slug":"monge-sam-robust-reparameterization-invariant","title":"Monge SAM: Robust Reparameterization-Invariant Sharpness-Aware Minimization Based on Loss Geometry","date":"2025-02-12","arxiv_id":"2502.08448","n_code_links":0,"syntology":null},{"paper":"/paper/towards-llm-unlearning-resilient-to","slug":"towards-llm-unlearning-resilient-to","title":"Towards LLM Unlearning Resilient to Relearning Attacks: A Sharpness-Aware Minimization Perspective and Beyond","date":"2025-02-07","arxiv_id":"2502.05374","n_code_links":1,"syntology":{"ran":5,"of":7,"n_ran_checked":3,"n_instrument":2,"unverified":2,"pointer_only":4,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","official":{"repos":["optml-group/unlearn-smooth"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/gcsam-gradient-centralized-sharpness-aware","slug":"gcsam-gradient-centralized-sharpness-aware","title":"GCSAM: Gradient Centralized Sharpness Aware Minimization","date":"2025-01-20","arxiv_id":"2501.11584","n_code_links":1,"syntology":null},{"paper":null,"slug":"weight-averaging-for-out-of-distribution","title":"Weight Averaging for Out-of-Distribution Generalization and Few-Shot Domain Adaptation","date":"2025-01-14","arxiv_id":"2501.08361","n_code_links":0,"syntology":null},{"paper":null,"slug":"preconditioned-sharpness-aware-minimization","title":"Preconditioned Sharpness-Aware Minimization: Unifying Analysis and a Novel Learning Algorithm","date":"2025-01-11","arxiv_id":"2501.06603","n_code_links":0,"syntology":null},{"paper":null,"slug":"safer-sharpness-aware-layer-selective","title":"SAFER: Sharpness Aware layer-selective Finetuning for Enhanced Robustness in vision transformers","date":"2025-01-02","arxiv_id":"2501.01529","n_code_links":0,"syntology":null},{"paper":null,"slug":"uncertainty-guided-cross-attention-ensemble","title":"Uncertainty-Guided Cross Attention Ensemble Mean Teacher for Semi-supervised Medical Image Segmentation","date":"2024-12-19","arxiv_id":"2412.15380","n_code_links":0,"syntology":null},{"paper":null,"slug":"seeking-consistent-flat-minima-for-better","title":"Seeking Consistent Flat Minima for Better Domain Generalization via Refining Loss Landscapes","date":"2024-12-18","arxiv_id":"2412.13573","n_code_links":0,"syntology":null},{"paper":"/paper/sse-sam-balancing-head-and-tail-classes","slug":"sse-sam-balancing-head-and-tail-classes","title":"SSE-SAM: Balancing Head and Tail Classes Gradually through Stage-Wise SAM","date":"2024-12-18","arxiv_id":"2412.13715","n_code_links":1,"syntology":null},{"paper":null,"slug":"meta-curvature-aware-minimization-for-domain","title":"Meta Curvature-Aware Minimization for Domain Generalization","date":"2024-12-16","arxiv_id":"2412.11542","n_code_links":0,"syntology":null},{"paper":null,"slug":"gaqat-gradient-adaptive-quantization-aware","title":"GAQAT: gradient-adaptive quantization-aware training for domain generalization","date":"2024-12-07","arxiv_id":"2412.05551","n_code_links":0,"syntology":null},{"paper":null,"slug":"towards-understanding-the-role-of-sharpness","title":"Towards Understanding the Role of Sharpness-Aware Minimization Algorithms for Out-of-Distribution Generalization","date":"2024-12-06","arxiv_id":"2412.05169","n_code_links":0,"syntology":null},{"paper":"/paper/beyond-local-sharpness-communication","slug":"beyond-local-sharpness-communication","title":"Beyond Local Sharpness: Communication-Efficient Global Sharpness-aware Minimization for Federated Learning","date":"2024-12-04","arxiv_id":"2412.03752","n_code_links":2,"syntology":null},{"paper":"/paper/federated-motor-imagery-classification-for","slug":"federated-motor-imagery-classification-for","title":"Federated Motor Imagery Classification for Privacy-Preserving Brain-Computer Interfaces","date":"2024-12-02","arxiv_id":"2412.01079","n_code_links":1,"syntology":null},{"paper":null,"slug":"improving-resistance-to-noisy-label-fitting","title":"Improving Resistance to Noisy Label Fitting by Reweighting Gradient in SAM","date":"2024-11-26","arxiv_id":"2411.17132","n_code_links":0,"syntology":null},{"paper":null,"slug":"reliable-poisoned-sample-detection-against","title":"Reliable Poisoned Sample Detection against Backdoor Attacks Enhanced by Sharpness Aware Minimization","date":"2024-11-18","arxiv_id":"2411.11525","n_code_links":0,"syntology":null},{"paper":"/paper/improving-visual-prompt-tuning-by-gaussian","slug":"improving-visual-prompt-tuning-by-gaussian","title":"Improving Visual Prompt Tuning by Gaussian Neighborhood Minimization for Long-Tailed Visual Recognition","date":"2024-10-28","arxiv_id":"2410.21042","n_code_links":3,"syntology":{"ran":3,"of":8,"n_ran_checked":1,"n_instrument":2,"unverified":5,"pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 5 unverified","official":{"repos":["keke921/gnm-pt"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":5,"ran_from_kinds":["official"]}}},{"paper":"/paper/fast-graph-sharpness-aware-minimization-for","slug":"fast-graph-sharpness-aware-minimization-for","title":"Fast Graph Sharpness-Aware Minimization for Enhancing and Accelerating Few-Shot Node Classification","date":"2024-10-22","arxiv_id":"2410.16845","n_code_links":1,"syntology":{"ran":3,"of":5,"n_ran_checked":1,"n_instrument":2,"unverified":2,"pointer_only":5,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","official":{"repos":["draym28/fgsam_neurips24"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"sharpness-aware-black-box-optimization","title":"Sharpness-Aware Black-Box Optimization","date":"2024-10-16","arxiv_id":"2410.12457","n_code_links":0,"syntology":null},{"paper":null,"slug":"bi-tta-bidirectional-test-time-adapter-for","title":"Bi-TTA: Bidirectional Test-Time Adapter for Remote Physiological Measurement","date":"2024-09-25","arxiv_id":"2409.17316","n_code_links":0,"syntology":null},{"paper":null,"slug":"flat-lora-low-rank-adaption-over-a-flat-loss","title":"Flat-LoRA: Low-Rank Adaption over a Flat Loss Landscape","date":"2024-09-22","arxiv_id":"2409.14396","n_code_links":0,"syntology":null},{"paper":"/paper/uu-mamba-uncertainty-aware-u-mamba-for-1","slug":"uu-mamba-uncertainty-aware-u-mamba-for-1","title":"UU-Mamba: Uncertainty-aware U-Mamba for Cardiovascular Segmentation","date":"2024-09-22","arxiv_id":"2409.14305","n_code_links":1,"syntology":null},{"paper":null,"slug":"dp-2-fedsam-enhancing-differentially-private","title":"DP$^2$-FedSAM: Enhancing Differentially Private Federated Learning Through Personalized Sharpness-Aware Minimization","date":"2024-09-20","arxiv_id":"2409.13645","n_code_links":0,"syntology":null},{"paper":null,"slug":"convergence-of-sharpness-aware-minimization","title":"Convergence of Sharpness-Aware Minimization Algorithms using Increasing Batch Size and Decaying Learning Rate","date":"2024-09-16","arxiv_id":"2409.09984","n_code_links":0,"syntology":null},{"paper":"/paper/cosco-a-sharpness-aware-training-framework","slug":"cosco-a-sharpness-aware-training-framework","title":"COSCO: A Sharpness-Aware Training Framework for Few-shot Multivariate Time Series Classification","date":"2024-09-15","arxiv_id":"2409.09645","n_code_links":1,"syntology":null},{"paper":"/paper/htr-vt-handwritten-text-recognition-with","slug":"htr-vt-handwritten-text-recognition-with","title":"HTR-VT: Handwritten Text Recognition with Vision Transformer","date":"2024-09-13","arxiv_id":"2409.08573","n_code_links":2,"syntology":null},{"paper":null,"slug":"neighborhood-and-global-perturbations","title":"Neighborhood and Global Perturbations Supported SAM in Federated Learning: From Local Tweaks To Global Awareness","date":"2024-08-26","arxiv_id":"2408.14144","n_code_links":0,"syntology":null},{"paper":null,"slug":"enhancing-sharpness-aware-minimization-by","title":"Enhancing Sharpness-Aware Minimization by Learning Perturbation Radius","date":"2024-08-15","arxiv_id":"2408.08222","n_code_links":0,"syntology":null},{"paper":null,"slug":"do-sharpness-based-optimizers-improve","title":"Do Sharpness-based Optimizers Improve Generalization in Medical Image Analysis?","date":"2024-08-07","arxiv_id":"2408.04065","n_code_links":0,"syntology":null},{"paper":"/paper/making-robust-generalizers-less-rigid-with","slug":"making-robust-generalizers-less-rigid-with","title":"Making Robust Generalizers Less Rigid with Loss Concentration","date":"2024-08-07","arxiv_id":"2408.03619","n_code_links":1,"syntology":null},{"paper":null,"slug":"u-medsam-uncertainty-aware-medsam-for-medical","title":"Challenge Summary U-MedSAM: Uncertainty-aware MedSAM for Medical Image Segmentation","date":"2024-08-03","arxiv_id":"2408.08881","n_code_links":0,"syntology":null},{"paper":"/paper/improving-sam-requires-rethinking-its","slug":"improving-sam-requires-rethinking-its","title":"Improving SAM Requires Rethinking its Optimization Formulation","date":"2024-07-17","arxiv_id":"2407.12993","n_code_links":1,"syntology":{"ran":4,"of":4,"n_ran_checked":1,"n_instrument":3,"unverified":0,"pointer_only":0,"phrase":"4 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","official":{"repos":["LIONS-EPFL/BiSAM"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"exploring-energy-based-models-for-out-of","title":"Exploring Energy-Based Models for Out-of-Distribution Detection in Dialect Identification","date":"2024-06-26","arxiv_id":"2406.18067","n_code_links":0,"syntology":null},{"paper":"/paper/improving-robustness-to-corruptions-with","slug":"improving-robustness-to-corruptions-with","title":"Improving robustness to corruptions with multiplicative weight perturbations","date":"2024-06-24","arxiv_id":"2406.16540","n_code_links":1,"syntology":{"ran":7,"of":9,"n_ran_checked":4,"n_instrument":3,"unverified":2,"pointer_only":9,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 3 honoured, 1 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified","official":{"repos":["trungtrinh44/damp"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/adaptive-adversarial-cross-entropy-loss-for","slug":"adaptive-adversarial-cross-entropy-loss-for","title":"Adaptive Adversarial Cross-Entropy Loss for Sharpness-Aware Minimization","date":"2024-06-20","arxiv_id":"2406.14329","n_code_links":1,"syntology":null},{"paper":"/paper/forget-sharpness-perturbed-forgetting-of","slug":"forget-sharpness-perturbed-forgetting-of","title":"Forget Sharpness: Perturbed Forgetting of Model Biases Within SAM Dynamics","date":"2024-06-10","arxiv_id":"2406.06700","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["borealisai/perturbed-forgetting"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/revisiting-catastrophic-forgetting-in-large","slug":"revisiting-catastrophic-forgetting-in-large","title":"Revisiting Catastrophic Forgetting in Large Language Model Tuning","date":"2024-06-07","arxiv_id":"2406.04836","n_code_links":1,"syntology":null},{"paper":"/paper/a-universal-class-of-sharpness-aware","slug":"a-universal-class-of-sharpness-aware","title":"A Universal Class of Sharpness-Aware Minimization Algorithms","date":"2024-06-06","arxiv_id":"2406.03682","n_code_links":1,"syntology":{"ran":5,"of":6,"n_ran_checked":3,"n_instrument":2,"unverified":1,"pointer_only":0,"phrase":"5 ran (of which 2 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 1 violated, 2 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","official":{"repos":["dbahri/universal_sam"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":2,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/improving-generalization-and-convergence-by","slug":"improving-generalization-and-convergence-by","title":"Improving Generalization and Convergence by Enhancing Implicit Regularization","date":"2024-05-31","arxiv_id":"2405.20763","n_code_links":1,"syntology":{"ran":7,"of":7,"n_ran_checked":4,"n_instrument":3,"unverified":0,"pointer_only":7,"phrase":"7 ran (of which 1 constructed an object rather than computing a result; 4 with no instrument failure: 2 honoured, 0 violated, 2 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","official":{"repos":["wmz9/ire-algorithm-framework"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":1,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/domain-inspired-sharpness-aware-minimization","slug":"domain-inspired-sharpness-aware-minimization","title":"Domain-Inspired Sharpness-Aware Minimization Under Domain Shifts","date":"2024-05-29","arxiv_id":"2405.18861","n_code_links":1,"syntology":{"ran":5,"of":5,"n_ran_checked":3,"n_instrument":2,"unverified":0,"pointer_only":5,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["mediabrain-sjtu/disam"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/locally-estimated-global-perturbations-are","slug":"locally-estimated-global-perturbations-are","title":"Locally Estimated Global Perturbations are Better than Local Perturbations for Federated Sharpness-aware Minimization","date":"2024-05-29","arxiv_id":"2405.18890","n_code_links":1,"syntology":null},{"paper":"/paper/does-sgd-really-happen-in-tiny-subspaces","slug":"does-sgd-really-happen-in-tiny-subspaces","title":"Does SGD really happen in tiny subspaces?","date":"2024-05-25","arxiv_id":"2405.16002","n_code_links":0,"syntology":{"ran":14,"of":15,"n_ran_checked":9,"n_instrument":5,"unverified":1,"pointer_only":15,"phrase":"14 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 6 honoured, 0 violated, 3 with no contract checked; 5 where Syntology's instrument failed) · 1 unverified","official":null}},{"paper":"/paper/uu-mamba-uncertainty-aware-u-mamba-for","slug":"uu-mamba-uncertainty-aware-u-mamba-for","title":"UU-Mamba: Uncertainty-aware U-Mamba for Cardiac Image Segmentation","date":"2024-05-25","arxiv_id":"2405.17496","n_code_links":1,"syntology":null},{"paper":null,"slug":"saddle-sharpness-aware-decentralized-deep","title":"SADDLe: Sharpness-Aware Decentralized Deep Learning with Heterogeneous Data","date":"2024-05-22","arxiv_id":"2405.13961","n_code_links":0,"syntology":null},{"paper":null,"slug":"sharpness-aware-minimization-for-evolutionary","title":"Sharpness-Aware Minimization for Evolutionary Feature Construction in Regression","date":"2024-05-11","arxiv_id":"2405.06869","n_code_links":0,"syntology":null},{"paper":null,"slug":"make-the-most-of-your-data-changing-the","title":"Changing the Training Data Distribution to Reduce Simplicity Bias Improves In-distribution Generalization","date":"2024-04-27","arxiv_id":"2404.17768","n_code_links":0,"syntology":null},{"paper":"/paper/revisiting-random-weight-perturbation-for","slug":"revisiting-random-weight-perturbation-for","title":"Revisiting Random Weight Perturbation for Efficiently Improving Generalization","date":"2024-03-30","arxiv_id":"2404.00357","n_code_links":1,"syntology":{"ran":5,"of":9,"n_ran_checked":4,"n_instrument":1,"unverified":4,"pointer_only":9,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 2 honoured, 1 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified","official":{"repos":["nblt/marwp"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"unknown-domain-inconsistency-minimization-for","title":"Unknown Domain Inconsistency Minimization for Domain Generalization","date":"2024-03-12","arxiv_id":"2403.07329","n_code_links":0,"syntology":null},{"paper":null,"slug":"dpadapter-improving-differentially-private","title":"DPAdapter: Improving Differentially Private Deep Learning through Noise Tolerance Pre-training","date":"2024-03-05","arxiv_id":"2403.02571","n_code_links":0,"syntology":null},{"paper":"/paper/flatnas-optimizing-flatness-in-neural","slug":"flatnas-optimizing-flatness-in-neural","title":"FlatNAS: optimizing Flatness in Neural Architecture Search for Out-of-Distribution Robustness","date":"2024-02-29","arxiv_id":"2402.19102","n_code_links":2,"syntology":null},{"paper":"/paper/helen-optimizing-ctr-prediction-models-with","slug":"helen-optimizing-ctr-prediction-models-with","title":"Helen: Optimizing CTR Prediction Models with Frequency-wise Hessian Eigenvalue Regularization","date":"2024-02-23","arxiv_id":"2403.00798","n_code_links":1,"syntology":null},{"paper":"/paper/on-the-duality-between-sharpness-aware","slug":"on-the-duality-between-sharpness-aware","title":"On the Duality Between Sharpness-Aware Minimization and Adversarial Training","date":"2024-02-23","arxiv_id":"2402.15152","n_code_links":1,"syntology":{"ran":4,"of":8,"n_ran_checked":2,"n_instrument":2,"unverified":4,"pointer_only":8,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 1 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 4 unverified","official":{"repos":["weizeming/sam_at"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":"/paper/stabilizing-sharpness-aware-minimization","slug":"stabilizing-sharpness-aware-minimization","title":"Stabilizing Sharpness-aware Minimization Through A Simple Renormalization Strategy","date":"2024-01-14","arxiv_id":"2401.07250","n_code_links":2,"syntology":null},{"paper":"/paper/cr-sam-curvature-regularized-sharpness-aware","slug":"cr-sam-curvature-regularized-sharpness-aware","title":"CR-SAM: Curvature Regularized Sharpness-Aware Minimization","date":"2023-12-21","arxiv_id":"2312.13555","n_code_links":1,"syntology":{"ran":7,"of":11,"n_ran_checked":3,"n_instrument":4,"unverified":4,"pointer_only":11,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 4 where Syntology's instrument failed) · 4 unverified","official":{"repos":["trustaiot/cr-sam"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":"/paper/unveiling-empirical-pathologies-of-laplace","slug":"unveiling-empirical-pathologies-of-laplace","title":"Identity Curvature Laplace Approximation for Improved Out-of-Distribution Detection","date":"2023-12-16","arxiv_id":"2312.10464","n_code_links":1,"syntology":null},{"paper":"/paper/the-effects-of-overparameterization-on","slug":"the-effects-of-overparameterization-on","title":"Critical Influence of Overparameterization on Sharpness-aware Minimization","date":"2023-11-29","arxiv_id":"2311.17539","n_code_links":1,"syntology":{"ran":5,"of":9,"n_ran_checked":5,"n_instrument":0,"unverified":4,"pointer_only":9,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","official":{"repos":["log-postech/sam-overparam"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"lightweight-face-recognition-an-improved","title":"Lightweight Face Recognition: An Improved MobileFaceNet Model","date":"2023-11-26","arxiv_id":"2311.15326","n_code_links":0,"syntology":null},{"paper":"/paper/flatness-aware-adversarial-attack","slug":"flatness-aware-adversarial-attack","title":"Transferability Bound Theory: Exploring Relationship between Adversarial Transferability and Flatness","date":"2023-11-10","arxiv_id":"2311.06423","n_code_links":1,"syntology":{"ran":8,"of":12,"n_ran_checked":4,"n_instrument":4,"unverified":4,"pointer_only":12,"phrase":"8 ran (of which 2 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 4 where Syntology's instrument failed) · 4 unverified","official":{"repos":["fmy266/tpa"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":2,"n_ran_no_instrument_failure":4,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"outliers-with-opposing-signals-have-an","title":"Outliers with Opposing Signals Have an Outsized Effect on Neural Network Optimization","date":"2023-11-07","arxiv_id":"2311.04163","n_code_links":0,"syntology":null},{"paper":"/paper/implicit-regularization-via-soft-ascent","slug":"implicit-regularization-via-soft-ascent","title":"Soft ascent-descent as a stable and flexible alternative to flooding","date":"2023-10-16","arxiv_id":"2310.10006","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":1,"n_instrument":1,"unverified":0,"pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["feedbackward/bdd-flood"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"why-does-sharpness-aware-minimization","title":"Why Does Sharpness-Aware Minimization Generalize Better Than SGD?","date":"2023-10-11","arxiv_id":"2310.07269","n_code_links":0,"syntology":null},{"paper":"/paper/tram-bridging-trust-regions-and-sharpness","slug":"tram-bridging-trust-regions-and-sharpness","title":"TRAM: Bridging Trust Regions and Sharpness Aware Minimization","date":"2023-10-05","arxiv_id":"2310.03646","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result","official":{"repos":["tomsherborne/tram_optimizer"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"rsam-learning-on-manifolds-with-riemannian","title":"RSAM: Learning on manifolds with Riemannian Sharpness-aware Minimization","date":"2023-09-29","arxiv_id":"2309.17215","n_code_links":0,"syntology":null},{"paper":null,"slug":"riemannian-sam-sharpness-aware-minimization","title":"Riemannian SAM: Sharpness-Aware Minimization on Riemannian Manifolds","date":"2023-09-21","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/sharpness-aware-minimization-and-the-edge-of","slug":"sharpness-aware-minimization-and-the-edge-of","title":"Sharpness-Aware Minimization and the Edge of Stability","date":"2023-09-21","arxiv_id":"2309.12488","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["google-deepmind/sam_edge"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"gradient-constrained-sharpness-aware-prompt","title":"Gradient constrained sharpness-aware prompt learning for vision-language models","date":"2023-09-14","arxiv_id":"2309.07866","n_code_links":0,"syntology":null},{"paper":null,"slug":"enhancing-transformers-without-self","title":"Enhancing Transformers without Self-supervised Learning: A Loss Landscape Perspective in Sequential Recommendation","date":"2023-08-20","arxiv_id":"2308.10347","n_code_links":0,"syntology":null},{"paper":null,"slug":"dfedadmm-dual-constraints-controlled-model","title":"DFedADMM: Dual Constraints Controlled Model Inconsistency for Decentralized Federated Learning","date":"2023-08-16","arxiv_id":"2308.08290","n_code_links":0,"syntology":null},{"paper":"/paper/imbsam-a-closer-look-at-sharpness-aware","slug":"imbsam-a-closer-look-at-sharpness-aware","title":"ImbSAM: A Closer Look at Sharpness-Aware Minimization in Class-Imbalanced Recognition","date":"2023-08-15","arxiv_id":"2308.07815","n_code_links":2,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["cool-xuan/imbalanced_sam"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"g-mix-a-generalized-mixup-learning-framework","title":"G-Mix: A Generalized Mixup Learning Framework Towards Flat Minima","date":"2023-08-07","arxiv_id":"2308.03236","n_code_links":0,"syntology":null},{"paper":"/paper/lookbehind-optimizer-k-steps-back-1-step","slug":"lookbehind-optimizer-k-steps-back-1-step","title":"Lookbehind-SAM: k steps back, 1 step forward","date":"2023-07-31","arxiv_id":"2307.16704","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":3,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"3 ran (of which 3 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; every one of the 3 samples that ran constructed an object rather than computing a result","official":{"repos":["chandar-lab/lookbehind-sam"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":3,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/towards-understanding-adversarial","slug":"towards-understanding-adversarial","title":"Why Does Little Robustness Help? A Further Step Towards Understanding Adversarial Transferability","date":"2023-07-15","arxiv_id":"2307.07873","n_code_links":1,"syntology":{"ran":12,"of":15,"n_ran_checked":6,"n_instrument":6,"unverified":3,"pointer_only":7,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 6 where Syntology's instrument failed) · 3 unverified","official":{"repos":["cgcl-codes/transferattacksurrogates"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":"/paper/systematic-investigation-of-sparse-perturbed","slug":"systematic-investigation-of-sparse-perturbed","title":"Systematic Investigation of Sparse Perturbed Sharpness-Aware Minimization Optimizer","date":"2023-06-30","arxiv_id":"2306.17504","n_code_links":1,"syntology":null},{"paper":"/paper/the-split-matters-flat-minima-methods-for","slug":"the-split-matters-flat-minima-methods-for","title":"The Split Matters: Flat Minima Methods for Improving the Performance of GNNs","date":"2023-06-15","arxiv_id":"2306.09121","n_code_links":1,"syntology":null},{"paper":"/paper/noise-stability-optimization-for-flat-minima","slug":"noise-stability-optimization-for-flat-minima","title":"Noise Stability Optimization for Finding Flat Minima: A Hessian-based Regularization Approach","date":"2023-06-14","arxiv_id":"2306.08553","n_code_links":1,"syntology":{"ran":13,"of":15,"n_ran_checked":12,"n_instrument":1,"unverified":2,"pointer_only":0,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 0 violated, 12 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","official":{"repos":["virtuosoresearch/noise-stability-optimization"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":12,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/differentially-private-sharpness-aware","slug":"differentially-private-sharpness-aware","title":"Differentially Private Sharpness-Aware Training","date":"2023-06-09","arxiv_id":"2306.05651","n_code_links":1,"syntology":{"ran":9,"of":11,"n_ran_checked":9,"n_instrument":0,"unverified":2,"pointer_only":1,"phrase":"9 ran (of which 1 constructed an object rather than computing a result; 9 with no instrument failure: 1 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","official":{"repos":["jinseongp/dpsat"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["found_in_text","official"]}}},{"paper":"/paper/optimal-transport-model-distributional","slug":"optimal-transport-model-distributional","title":"Optimal Transport Model Distributional Robustness","date":"2023-06-07","arxiv_id":"2306.04178","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":1,"phrase":"1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result","official":{"repos":["anh-ntv/ot_mdr"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/decentralized-sgd-and-average-direction-sam","slug":"decentralized-sgd-and-average-direction-sam","title":"Decentralized SGD and Average-direction SAM are Asymptotically Equivalent","date":"2023-06-05","arxiv_id":"2306.02913","n_code_links":1,"syntology":{"ran":8,"of":10,"n_ran_checked":6,"n_instrument":2,"unverified":2,"pointer_only":2,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","official":{"repos":["raiden-zhu/icml-2023-dsgd-and-sam"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/sharpness-aware-minimization-revisited","slug":"sharpness-aware-minimization-revisited","title":"Sharpness-Aware Minimization Revisited: Weighted Sharpness as a Regularization Term","date":"2023-05-25","arxiv_id":"2305.15817","n_code_links":1,"syntology":null},{"paper":"/paper/on-the-relation-between-sharpness-aware","slug":"on-the-relation-between-sharpness-aware","title":"Sharpness-Aware Minimization Alone can Improve Adversarial Robustness","date":"2023-05-09","arxiv_id":"2305.05392","n_code_links":1,"syntology":null},{"paper":"/paper/self-discipline-on-multiple-channels","slug":"self-discipline-on-multiple-channels","title":"Self-discipline on multiple channels","date":"2023-04-27","arxiv_id":"2304.14224","n_code_links":1,"syntology":null},{"paper":null,"slug":"enhancing-fine-tuning-based-backdoor-defense","title":"Enhancing Fine-Tuning Based Backdoor Defense with Sharpness-Aware Minimization","date":"2023-04-24","arxiv_id":"2304.11823","n_code_links":0,"syntology":null},{"paper":"/paper/sharpness-aware-gradient-matching-for-domain","slug":"sharpness-aware-gradient-matching-for-domain","title":"Sharpness-Aware Gradient Matching for Domain Generalization","date":"2023-03-18","arxiv_id":"2303.10353","n_code_links":1,"syntology":{"ran":10,"of":15,"n_ran_checked":8,"n_instrument":2,"unverified":5,"pointer_only":1,"phrase":"10 ran (of which 8 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 2 where Syntology's instrument failed) · 5 unverified","official":{"repos":["wang-pengfei/sagm"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":8,"n_ran_no_instrument_failure":8,"n_unverified":5,"ran_from_kinds":["official","unlocated"]}}}],"papers_shown":100,"papers_order":"date (newest first), then slug","paper_counts":{"archive_papers_tagged":142,"with_a_code_link":70,"where_syntology_ran_a_sample":34,"not_listed_spam_title":0,"listed":142,"listed_where_code_ran":34,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":32,"every_run_a_failure_of_syntologys_instrument":2,"listed_with_a_run_with_no_instrument_failure":32,"listed_every_run_a_failure_of_syntologys_instrument":2,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"papers_where_code_ran":34,"papers_where_code_ran_first_page":"/method/sharpness-aware-minimization/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not isolate this method inside it.","pages":[{"order":"archive","page":2,"of":2,"url":"/method/sharpness-aware-minimization/papers/2","json":"/method/sharpness-aware-minimization/papers/2.json","rows":42},{"order":"ran","page":1,"of":1,"url":"/method/sharpness-aware-minimization/papers/ran/1","json":"/method/sharpness-aware-minimization/papers/ran/1.json","rows":34}],"tasks":[{"task":"/task/image-classification","name":"Image Classification","papers":19},{"task":"/task/image-classification","name":"image-classification","papers":13},{"task":"/task/data-augmentation","name":"Data Augmentation","papers":10},{"task":"/task/domain-generalization","name":"Domain Generalization","papers":10},{"task":"/task/federated-learning","name":"Federated Learning","papers":8},{"task":"/task/model","name":"model","papers":7},{"task":"/task/semantic-segmentation","name":"Semantic Segmentation","papers":6},{"task":"/task/computational-efficiency","name":"Computational Efficiency","papers":5},{"task":"/task/quantization","name":"Quantization","papers":5},{"task":"/task/segmentation","name":"Segmentation","papers":5},{"task":"/task/deep-learning","name":"Deep Learning","papers":4},{"task":"/task/adversarial-robustness","name":"Adversarial Robustness","papers":3},{"task":"/task/attribute","name":"Attribute","papers":3},{"task":"/task/classification-1","name":"Classification","papers":3},{"task":"/task/image-segmentation","name":"Image Segmentation","papers":3},{"task":"/task/language-modeling","name":"Language Modeling","papers":3},{"task":"/task/language-modelling","name":"Language Modelling","papers":3},{"task":"/task/long-tail-learning","name":"Long-tail Learning","papers":3},{"task":"/task/node-classification","name":"Node Classification","papers":3},{"task":"/task/out-of-distribution-detection","name":"Out-of-Distribution Detection","papers":3}],"tasks_shown":20,"n_tasks":115,"usage_by_year":[{"year":"2020","papers":1},{"year":"2021","papers":10},{"year":"2022","papers":27},{"year":"2023","papers":34},{"year":"2024","papers":47},{"year":"2025","papers":23}],"row_source":"methods_table","archive":{"source":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","archive_url":"https://paperswithcode.com/method/sharpness-aware-minimization"},"syntology_read_at":"2026-10-05T00:36:11+00:00","syntology":{"source":"Syntology's have check for this name (the free coverage lookup), read from Syntology's graph","have_url":"https://syntology.ai/api/graph/have?x=Sharpness-Aware%20Minimization","read_at":"2026-10-05T01:01:55+00:00","query":"Sharpness-Aware Minimization","kind":"paper","have":"unverified_code","tier":"harvested","verified_implementation":false,"level":1,"level_meaning":"the served verification level, per answer; never summed across methods","resolved_to":{"arxiv_id":"2503.02225"},"resolution":"paper","resolved_name_differs":false,"absence_asserted":false,"absence_unchecked":null,"no_code_is_about_this_method":false,"subject":"different_paper","archive_paper_arxiv_id":"2010.01412","repositories":{"listed":1,"in_graph":1,"list_truncated":false,"strongest_link":"official"},"retrieve_with":"get_harvested_code_for_paper(arxiv_id='2503.02225')","name_competition":{"verdict":"sole_bearer","may_be_wrong_sense":false,"bearers_found":1,"served":{"arxiv_id":"2503.02225","citations":null},"leading_other_bearer":null,"n_other_bearers_listed":0,"note":"Nothing else in this corpus is named 'Sharpness-Aware Minimization'. That is a statement about this corpus and not about the field: short names are reused, and a sense we never collected cannot show up here. Confirm `served.arxiv_id` if you had a specific paper in mind."},"name_competition_text":null,"near_matches":null,"code_nearby":[],"code_nearby_caption":null,"origin_paper":{"arxiv_id":"2503.02225","page":"/paper/sharpness-aware-minimization-general-analysis","syntology_url":"https://syntology.ai/paper/2503.02225","in_graph_layer":true,"samples":1,"ran":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","instrument_means":"failures of Syntology's instrument, not of the code"},"line":"about another paper, arXiv:2503.02225: harvested code stored, below machine verification (unverified_code; harvested), served level V1. Repositories: 1 listed of 1 in the graph, strongest link: official. The lookup matched a paper by its title, arXiv:2503.02225, not a method entry. About another paper: this answer is about arXiv:2503.02225, while the archive credits arXiv:2010.01412.","level_legend":{"state":"quoted","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","card_sha256":"479785a84658dd682a11b10237b3620d651d7f87799f5dc7add970aaa83f6d39","note":"Syntology's served verification levels, quoted verbatim from its MCP server card; a row is split where the card separates clauses with a double hyphen, and the separator is not reproduced","levels":[{"level":"V0","quoted":["imports"]},{"level":"V1","quoted":["executes against a synthesized fixture and returns a value of the recorded type"]},{"level":"V2","quoted":["two implementations GENERATED from the paper's signature and spec agree numerically (1e-6) on fixture inputs","neither of the two ever read the authors' own code, so V2 measures how unambiguously the paper specifies the method, not fidelity to the authors' implementation (measured 2026-09-11, commit 75eaa77: cross_checked_by is a second LLM on 2,628 of 2,831 served samples)"]},{"level":"V3","quoted":["paper-derived property tests pass on both of those same two generations."]}],"no_rung":"No rung on this ladder compares the served code against the authors' implementation, so treat every level as evidence about runnability and internal agreement, not about matching the paper's results."}},"syntology_have_state":"loaded","record_sha256":"4ae8f550f1a3674feddf732a54c41417fd3d1446e598758917437b318dbf0a43","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}