{"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":"/task/second-order-methods","name":"Second-order methods","slug":"second-order-methods","description_markdown":"Use second-order statistics to process data.","categories":[],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"derived"},"counts":{"papers_tagged":181,"papers_with_code":52,"benchmarks":0,"benchmark_tables_in_archive":0,"benchmark_tables_shown":0,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":0,"subtasks":0,"parent_tasks":0},"benchmarks":[],"datasets":[],"subtasks":[],"parent_tasks":[],"papers":{"order":"repositories listed in the archive (most first), then date (newest first), then slug; the archive holds no stars","population":"every paper the archive tags with this task (distinct papers; spam titles not listed). 'of' counts the papers listed; until 2026-09-25 it counted only the papers with a code link, and that number is of_with_code","page":1,"pages_in_order":2,"rows_per_page":100,"shown":100,"of":181,"of_with_code":52,"tagged_in_all":181,"counts":{"archive_papers_tagged":181,"with_a_code_link":52,"where_syntology_ran_a_sample":12,"not_listed_spam_title":0,"listed":181,"listed_where_code_ran":12,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":11,"every_run_a_failure_of_syntologys_instrument":1,"listed_with_a_run_with_no_instrument_failure":11,"listed_every_run_a_failure_of_syntologys_instrument":1,"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"},"items":[{"url":"/paper/adahessian-an-adaptive-second-order-optimizer","slug":"adahessian-an-adaptive-second-order-optimizer","title":"ADAHESSIAN: An Adaptive Second Order Optimizer for Machine Learning","date":"2020-06-01","arxiv_id":"2006.00719","repositories_listed":4,"syntology":{"n":11,"n_ran":5,"n_constructed":0,"n_ran_checked":4,"n_instrument":1,"n_unverified":6,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":1,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/adahessian-an-adaptive-second-order-optimizer#ran","syntology_url":"https://syntology.ai/paper/2006.00719","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.00719"}},"official":{"repos":["amirgholami/adahessian"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":5,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/second-order-stochastic-optimization-for","slug":"second-order-stochastic-optimization-for","title":"Second-Order Stochastic Optimization for Machine Learning in Linear Time","date":"2016-02-12","arxiv_id":"1602.03943","repositories_listed":4,"syntology":null},{"url":"/paper/can-we-remove-the-square-root-in-adaptive","slug":"can-we-remove-the-square-root-in-adaptive","title":"Can We Remove the Square-Root in Adaptive Gradient Methods? A Second-Order Perspective","date":"2024-02-05","arxiv_id":"2402.03496","repositories_listed":2,"syntology":{"n":10,"n_ran":9,"n_constructed":0,"n_ran_checked":5,"n_instrument":4,"n_unverified":1,"n_honours":3,"n_violates":1,"n_no_contract":1,"n_pointer_only":9,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 3 honoured, 1 violated, 1 with no contract checked; 4 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/can-we-remove-the-square-root-in-adaptive#ran","syntology_url":"https://syntology.ai/paper/2402.03496","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.03496"}},"official":{"repos":["f-dangel/sirfshampoo","yorkerlin/remove-the-square-root"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/structured-inverse-free-natural-gradient","slug":"structured-inverse-free-natural-gradient","title":"Structured Inverse-Free Natural Gradient: Memory-Efficient & Numerically-Stable KFAC","date":"2023-12-09","arxiv_id":"2312.05705","repositories_listed":2,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_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","sample_list":"/paper/structured-inverse-free-natural-gradient#ran","syntology_url":"https://syntology.ai/paper/2312.05705","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.05705"}},"official":{"repos":["f-dangel/singd"],"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"]}}},{"url":"/paper/near-out-of-distribution-detection-for-low","slug":"near-out-of-distribution-detection-for-low","title":"Near out-of-distribution detection for low-resolution radar micro-Doppler signatures","date":"2022-05-12","arxiv_id":"2205.07869","repositories_listed":2,"syntology":null},{"url":"/paper/efficient-matrix-free-approximations-of","slug":"efficient-matrix-free-approximations-of","title":"M-FAC: Efficient Matrix-Free Approximations of Second-Order Information","date":"2021-07-07","arxiv_id":"2107.03356","repositories_listed":2,"syntology":{"n":14,"n_ran":7,"n_constructed":0,"n_ran_checked":4,"n_instrument":3,"n_unverified":7,"n_honours":4,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 4 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 7 unverified","sample_list":"/paper/efficient-matrix-free-approximations-of#ran","syntology_url":"https://syntology.ai/paper/2107.03356","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2107.03356"}},"official":{"repos":["IST-DASLab/M-FAC"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/on-the-promise-of-the-stochastic-generalized","slug":"on-the-promise-of-the-stochastic-generalized","title":"On the Promise of the Stochastic Generalized Gauss-Newton Method for Training DNNs","date":"2020-06-03","arxiv_id":"2006.02409","repositories_listed":2,"syntology":null},{"url":"/paper/low-rank-saddle-free-newton-algorithm-and","slug":"low-rank-saddle-free-newton-algorithm-and","title":"Low Rank Saddle Free Newton: A Scalable Method for Stochastic Nonconvex Optimization","date":"2020-02-07","arxiv_id":"2002.02881","repositories_listed":2,"syntology":null},{"url":"/paper/newtonian-monte-carlo-single-site-mcmc-meets","slug":"newtonian-monte-carlo-single-site-mcmc-meets","title":"Newtonian Monte Carlo: single-site MCMC meets second-order gradient methods","date":"2020-01-15","arxiv_id":"2001.05567","repositories_listed":2,"syntology":null},{"url":"/paper/nysact-a-scalable-preconditioned-gradient","slug":"nysact-a-scalable-preconditioned-gradient","title":"NysAct: A Scalable Preconditioned Gradient Descent using Nystrom Approximation","date":"2025-06-10","arxiv_id":"2506.08360","repositories_listed":1,"syntology":null},{"url":"/paper/towards-practical-second-order-optimizers-in","slug":"towards-practical-second-order-optimizers-in","title":"Towards Practical Second-Order Optimizers in Deep Learning: Insights from Fisher Information Analysis","date":"2025-04-26","arxiv_id":"2504.20096","repositories_listed":1,"syntology":null},{"url":"/paper/sassha-sharpness-aware-adaptive-second-order","slug":"sassha-sharpness-aware-adaptive-second-order","title":"SASSHA: Sharpness-aware Adaptive Second-order Optimization with Stable Hessian Approximation","date":"2025-02-25","arxiv_id":"2502.18153","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":1,"n_ran_checked":2,"n_instrument":1,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":1,"n_pointer_only":3,"phrase":"3 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/sassha-sharpness-aware-adaptive-second-order#ran","syntology_url":"https://syntology.ai/paper/2502.18153","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.18153"}},"official":{"repos":["LOG-postech/Sassha"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":1,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/online-covariance-matrix-estimation-in","slug":"online-covariance-matrix-estimation-in","title":"Online Covariance Matrix Estimation in Sketched Newton Methods","date":"2025-02-10","arxiv_id":"2502.07114","repositories_listed":1,"syntology":null},{"url":"/paper/exact-tractable-gauss-newton-optimization-in","slug":"exact-tractable-gauss-newton-optimization-in","title":"Exact, Tractable Gauss-Newton Optimization in Deep Reversible Architectures Reveal Poor Generalization","date":"2024-11-12","arxiv_id":"2411.07979","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 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; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/exact-tractable-gauss-newton-optimization-in#ran","syntology_url":"https://syntology.ai/paper/2411.07979","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.07979"}},"official":{"repos":["mtkresearch/exact_GN_revNN"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/an-adaptive-second-order-method-for-a-class","slug":"an-adaptive-second-order-method-for-a-class","title":"Alternating Iteratively Reweighted $\\ell_1$ and Subspace Newton Algorithms for Nonconvex Sparse Optimization","date":"2024-07-24","arxiv_id":"2407.17216","repositories_listed":1,"syntology":null},{"url":"/paper/revisiting-scalable-hessian-diagonal","slug":"revisiting-scalable-hessian-diagonal","title":"Revisiting Scalable Hessian Diagonal Approximations for Applications in Reinforcement Learning","date":"2024-06-05","arxiv_id":"2406.03276","repositories_listed":1,"syntology":null},{"url":"/paper/a-gauss-newton-approach-for-min-max","slug":"a-gauss-newton-approach-for-min-max","title":"A Gauss-Newton Approach for Min-Max Optimization in Generative Adversarial Networks","date":"2024-04-10","arxiv_id":"2404.07172","repositories_listed":1,"syntology":null},{"url":"/paper/sgd-with-partial-hessian-for-deep-neural","slug":"sgd-with-partial-hessian-for-deep-neural","title":"SGD with Partial Hessian for Deep Neural Networks Optimization","date":"2024-03-05","arxiv_id":"2403.02681","repositories_listed":1,"syntology":null},{"url":"/paper/adapting-newton-s-method-to-neural-networks","slug":"adapting-newton-s-method-to-neural-networks","title":"Adapting Newton's Method to Neural Networks through a Summary of Higher-Order Derivatives","date":"2023-12-06","arxiv_id":"2312.03885","repositories_listed":1,"syntology":null},{"url":"/paper/adasub-stochastic-optimization-using-second","slug":"adasub-stochastic-optimization-using-second","title":"AdaSub: Stochastic Optimization Using Second-Order Information in Low-Dimensional Subspaces","date":"2023-10-30","arxiv_id":"2310.20060","repositories_listed":1,"syntology":null},{"url":"/paper/adam-through-a-second-order-lens","slug":"adam-through-a-second-order-lens","title":"Studying K-FAC Heuristics by Viewing Adam through a Second-Order Lens","date":"2023-10-23","arxiv_id":"2310.14963","repositories_listed":1,"syntology":{"n":16,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":9,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":16,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 9 unverified","sample_list":"/paper/adam-through-a-second-order-lens#ran","syntology_url":"https://syntology.ai/paper/2310.14963","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.14963"}},"official":{"repos":["rmclarke/adamthroughasecondorderlens"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":9,"ran_from_kinds":["official"]}}},{"url":"/paper/error-feedback-can-accurately-compress","slug":"error-feedback-can-accurately-compress","title":"Error Feedback Can Accurately Compress Preconditioners","date":"2023-06-09","arxiv_id":"2306.06098","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/error-feedback-can-accurately-compress#ran","syntology_url":"https://syntology.ai/paper/2306.06098","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.06098"}},"official":{"repos":["ist-daslab/efcp"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/mkor-momentum-enabled-kronecker-factor-based","slug":"mkor-momentum-enabled-kronecker-factor-based","title":"MKOR: Momentum-Enabled Kronecker-Factor-Based Optimizer Using Rank-1 Updates","date":"2023-06-02","arxiv_id":"2306.01685","repositories_listed":1,"syntology":{"n":10,"n_ran":9,"n_constructed":2,"n_ran_checked":6,"n_instrument":3,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":10,"phrase":"9 ran (of which 2 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/mkor-momentum-enabled-kronecker-factor-based#ran","syntology_url":"https://syntology.ai/paper/2306.01685","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.01685"}},"official":{"repos":["mohammad-mozaffari/mkor"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":2,"n_ran_no_instrument_failure":6,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/sharpened-lazy-incremental-quasi-newton","slug":"sharpened-lazy-incremental-quasi-newton","title":"Sharpened Lazy Incremental Quasi-Newton Method","date":"2023-05-26","arxiv_id":"2305.17283","repositories_listed":1,"syntology":null},{"url":"/paper/isaac-newton-input-based-approximate","slug":"isaac-newton-input-based-approximate","title":"ISAAC Newton: Input-based Approximate Curvature for Newton's Method","date":"2023-05-01","arxiv_id":"2305.00604","repositories_listed":1,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 1 unverified","sample_list":"/paper/isaac-newton-input-based-approximate#ran","syntology_url":"https://syntology.ai/paper/2305.00604","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.00604"}},"official":{"repos":["felix-petersen/isaac"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"url":"/paper/automatic-gradient-descent-deep-learning","slug":"automatic-gradient-descent-deep-learning","title":"Automatic Gradient Descent: Deep Learning without Hyperparameters","date":"2023-04-11","arxiv_id":"2304.05187","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"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","sample_list":"/paper/automatic-gradient-descent-deep-learning#ran","syntology_url":"https://syntology.ai/paper/2304.05187","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2304.05187"}},"official":{"repos":["jxbz/agd"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/fosi-hybrid-first-and-second-order","slug":"fosi-hybrid-first-and-second-order","title":"FOSI: Hybrid First and Second Order Optimization","date":"2023-02-16","arxiv_id":"2302.08484","repositories_listed":1,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 1 unverified","sample_list":"/paper/fosi-hybrid-first-and-second-order#ran","syntology_url":"https://syntology.ai/paper/2302.08484","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2302.08484"}},"official":{"repos":["hsivan/fosi"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"url":"/paper/differentially-private-image-classification","slug":"differentially-private-image-classification","title":"Differentially Private Image Classification from Features","date":"2022-11-24","arxiv_id":"2211.13403","repositories_listed":1,"syntology":null},{"url":"/paper/the-hypervolume-indicator-hessian-matrix","slug":"the-hypervolume-indicator-hessian-matrix","title":"The Hypervolume Indicator Hessian Matrix: Analytical Expression, Computational Time Complexity, and Sparsity","date":"2022-11-08","arxiv_id":"2211.04171","repositories_listed":1,"syntology":null},{"url":"/paper/stochastic-variance-reduced-newton","slug":"stochastic-variance-reduced-newton","title":"Stochastic Variance-Reduced Newton: Accelerating Finite-Sum Minimization with Large Batches","date":"2022-06-06","arxiv_id":"2206.02702","repositories_listed":1,"syntology":null},{"url":"/paper/asymptotic-convergence-rate-and-statistical","slug":"asymptotic-convergence-rate-and-statistical","title":"Statistical Inference of Constrained Stochastic Optimization via Sketched Sequential Quadratic Programming","date":"2022-05-27","arxiv_id":"2205.13687","repositories_listed":1,"syntology":null},{"url":"/paper/symmetry-teleportation-for-accelerated","slug":"symmetry-teleportation-for-accelerated","title":"Symmetry Teleportation for Accelerated Optimization","date":"2022-05-21","arxiv_id":"2205.10637","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":2,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":2,"n_no_contract":0,"n_pointer_only":5,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 2 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/symmetry-teleportation-for-accelerated#ran","syntology_url":"https://syntology.ai/paper/2205.10637","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2205.10637"}},"official":{"repos":["rose-stl-lab/symmetry-teleportation"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/generalized-optimistic-methods-for-convex","slug":"generalized-optimistic-methods-for-convex","title":"Generalized Optimistic Methods for Convex-Concave Saddle Point Problems","date":"2022-02-19","arxiv_id":"2202.09674","repositories_listed":1,"syntology":null},{"url":"/paper/communication-efficient-stochastic-zeroth","slug":"communication-efficient-stochastic-zeroth","title":"Communication-Efficient Stochastic Zeroth-Order Optimization for Federated Learning","date":"2022-01-24","arxiv_id":"2201.09531","repositories_listed":1,"syntology":null},{"url":"/paper/second-order-neural-ode-optimizer","slug":"second-order-neural-ode-optimizer","title":"Second-Order Neural ODE Optimizer","date":"2021-09-29","arxiv_id":"2109.14158","repositories_listed":1,"syntology":{"n":2,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 2 unverified","sample_list":"/paper/second-order-neural-ode-optimizer#ran","syntology_url":"https://syntology.ai/paper/2109.14158","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2109.14158"}},"official":{"repos":["ghliu/snopt"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":[]}}},{"url":"/paper/nonlinear-matrix-recovery-using-optimization","slug":"nonlinear-matrix-recovery-using-optimization","title":"Nonlinear matrix recovery using optimization on the Grassmann manifold","date":"2021-09-13","arxiv_id":"2109.06095","repositories_listed":1,"syntology":null},{"url":"/paper/locoprop-enhancing-backprop-via-local-loss","slug":"locoprop-enhancing-backprop-via-local-loss","title":"LocoProp: Enhancing BackProp via Local Loss Optimization","date":"2021-06-11","arxiv_id":"2106.06199","repositories_listed":1,"syntology":null},{"url":"/paper/tensor-normal-training-for-deep-learning","slug":"tensor-normal-training-for-deep-learning","title":"Tensor Normal Training for Deep Learning Models","date":"2021-06-05","arxiv_id":"2106.02925","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"2 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; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/tensor-normal-training-for-deep-learning#ran","syntology_url":"https://syntology.ai/paper/2106.02925","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.02925"}},"official":{"repos":["renyiryry/tnt_neurips_2021"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/curvature-is-key-sub-sampled-loss-surfaces","slug":"curvature-is-key-sub-sampled-loss-surfaces","title":"Learning Rates as a Function of Batch Size: A Random Matrix Theory Approach to Neural Network Training","date":"2020-06-16","arxiv_id":"2006.09092","repositories_listed":1,"syntology":null},{"url":"/paper/differentiable-expected-hypervolume","slug":"differentiable-expected-hypervolume","title":"Differentiable Expected Hypervolume Improvement for Parallel Multi-Objective Bayesian Optimization","date":"2020-06-09","arxiv_id":"2006.05078","repositories_listed":1,"syntology":null},{"url":"/paper/towards-asymptotic-optimality-with","slug":"towards-asymptotic-optimality-with","title":"Asymptotic Analysis of Conditioned Stochastic Gradient Descent","date":"2020-06-04","arxiv_id":"2006.02745","repositories_listed":1,"syntology":null},{"url":"/paper/milenas-efficient-neural-architecture-search","slug":"milenas-efficient-neural-architecture-search","title":"MiLeNAS: Efficient Neural Architecture Search via Mixed-Level Reformulation","date":"2020-03-27","arxiv_id":"2003.12238","repositories_listed":1,"syntology":null},{"url":"/paper/stochastic-newton-and-cubic-newton-methods","slug":"stochastic-newton-and-cubic-newton-methods","title":"Stochastic Newton and Cubic Newton Methods with Simple Local Linear-Quadratic Rates","date":"2019-12-03","arxiv_id":"1912.01597","repositories_listed":1,"syntology":null},{"url":"/paper/fast-and-furious-convergence-stochastic","slug":"fast-and-furious-convergence-stochastic","title":"Fast and Furious Convergence: Stochastic Second Order Methods under Interpolation","date":"2019-10-11","arxiv_id":"1910.04920","repositories_listed":1,"syntology":null},{"url":"/paper/sgd-momentum-optimizer-with-step-estimation","slug":"sgd-momentum-optimizer-with-step-estimation","title":"SGD momentum optimizer with step estimation by online parabola model","date":"2019-07-16","arxiv_id":"1907.07063","repositories_listed":1,"syntology":null},{"url":"/paper/limitations-of-the-empirical-fisher","slug":"limitations-of-the-empirical-fisher","title":"Limitations of the Empirical Fisher Approximation for Natural Gradient Descent","date":"2019-05-29","arxiv_id":"1905.12558","repositories_listed":1,"syntology":null},{"url":"/paper/190409448","slug":"190409448","title":"LIBS2ML: A Library for Scalable Second Order Machine Learning Algorithms","date":"2019-04-20","arxiv_id":"1904.09448","repositories_listed":1,"syntology":null},{"url":"/paper/improving-sgd-convergence-by-tracing-multiple","slug":"improving-sgd-convergence-by-tracing-multiple","title":"Improving SGD convergence by online linear regression of gradients in multiple statistically relevant directions","date":"2019-01-31","arxiv_id":"1901.11457","repositories_listed":1,"syntology":null},{"url":"/paper/stochastic-trust-region-inexact-newton-method","slug":"stochastic-trust-region-inexact-newton-method","title":"Stochastic Trust Region Inexact Newton Method for Large-scale Machine Learning","date":"2018-12-26","arxiv_id":"1812.10426","repositories_listed":1,"syntology":null},{"url":"/paper/large-batch-size-training-of-neural-networks","slug":"large-batch-size-training-of-neural-networks","title":"Large batch size training of neural networks with adversarial training and second-order information","date":"2018-10-02","arxiv_id":"1810.01021","repositories_listed":1,"syntology":null},{"url":"/paper/online-second-order-methods-for-non-convex","slug":"online-second-order-methods-for-non-convex","title":"Online Second Order Methods for Non-Convex Stochastic Optimizations","date":"2018-03-26","arxiv_id":"1803.09383","repositories_listed":1,"syntology":null},{"url":"/paper/optimization-methods-for-supervised-machine","slug":"optimization-methods-for-supervised-machine","title":"Optimization Methods for Supervised Machine Learning: From Linear Models to Deep Learning","date":"2017-06-30","arxiv_id":"1706.10207","repositories_listed":1,"syntology":null},{"url":null,"slug":"2506-04432","title":"KOALA++: Efficient Kalman-Based Optimization of Neural Networks with Gradient-Covariance Products","date":"2025-06-04","arxiv_id":"2506.04432","repositories_listed":0,"syntology":null},{"url":null,"slug":"accelerated-training-of-federated-learning","title":"Accelerated Training of Federated Learning via Second-Order Methods","date":"2025-05-29","arxiv_id":"2505.23588","repositories_listed":0,"syntology":null},{"url":null,"slug":"representation-meets-optimization-training","title":"Representation Meets Optimization: Training PINNs and PIKANs for Gray-Box Discovery in Systems Pharmacology","date":"2025-04-10","arxiv_id":"2504.07379","repositories_listed":0,"syntology":null},{"url":null,"slug":"fedosaa-improving-federated-learning-with-one","title":"FedOSAA: Improving Federated Learning with One-Step Anderson Acceleration","date":"2025-03-14","arxiv_id":"2503.10961","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-survey-of-optimization-methods-for-training","title":"A Survey of Optimization Methods for Training DL Models: Theoretical Perspective on Convergence and Generalization","date":"2025-01-24","arxiv_id":"2501.14458","repositories_listed":0,"syntology":null},{"url":null,"slug":"distributed-quasi-newton-method-for-fair-and","title":"Distributed Quasi-Newton Method for Fair and Fast Federated Learning","date":"2025-01-18","arxiv_id":"2501.10877","repositories_listed":0,"syntology":null},{"url":null,"slug":"preconditioners-for-the-stochastic-training-1","title":"Preconditioners for the Stochastic Training of Neural Fields","date":"2025-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"gp-fl-model-based-hessian-estimation-for","title":"GP-FL: Model-Based Hessian Estimation for Second-Order Over-the-Air Federated Learning","date":"2024-12-05","arxiv_id":"2412.03867","repositories_listed":0,"syntology":null},{"url":null,"slug":"adaptive-coordinate-wise-step-sizes-for-quasi","title":"A Learn-to-Optimize Approach for Coordinate-Wise Step Sizes for Quasi-Newton Methods","date":"2024-11-25","arxiv_id":"2412.00059","repositories_listed":0,"syntology":null},{"url":null,"slug":"gradient-norm-regularization-second-order","title":"Gradient Norm Regularization Second-Order Algorithms for Solving Nonconvex-Strongly Concave Minimax Problems","date":"2024-11-24","arxiv_id":"2411.15769","repositories_listed":0,"syntology":null},{"url":null,"slug":"don-t-be-so-positive-negative-step-sizes-in","title":"Don't Be So Positive: Negative Step Sizes in Second-Order Methods","date":"2024-11-18","arxiv_id":"2411.11224","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-stochastic-cubic-newton-with","title":"Improving Stochastic Cubic Newton with Momentum","date":"2024-10-25","arxiv_id":"2410.19644","repositories_listed":0,"syntology":null},{"url":null,"slug":"second-order-min-max-optimization-with-lazy","title":"Second-Order Min-Max Optimization with Lazy Hessians","date":"2024-10-12","arxiv_id":"2410.09568","repositories_listed":0,"syntology":null},{"url":null,"slug":"unlocking-fednl-self-contained-compute","title":"Unlocking FedNL: Self-Contained Compute-Optimized Implementation","date":"2024-10-11","arxiv_id":"2410.08760","repositories_listed":0,"syntology":null},{"url":null,"slug":"adversarial-vulnerability-as-a-consequence-of","title":"Adversarial Vulnerability as a Consequence of On-Manifold Inseparibility","date":"2024-10-09","arxiv_id":"2410.06921","repositories_listed":0,"syntology":null},{"url":null,"slug":"flens-federated-learning-with-enhanced","title":"FLeNS: Federated Learning with Enhanced Nesterov-Newton Sketch","date":"2024-09-23","arxiv_id":"2409.15216","repositories_listed":0,"syntology":null},{"url":null,"slug":"fed-sophia-a-communication-efficient-second","title":"Fed-Sophia: A Communication-Efficient Second-Order Federated Learning Algorithm","date":"2024-06-10","arxiv_id":"2406.06655","repositories_listed":0,"syntology":null},{"url":null,"slug":"adaptive-and-optimal-second-order-optimistic","title":"Adaptive and Optimal Second-order Optimistic Methods for Minimax Optimization","date":"2024-06-04","arxiv_id":"2406.02016","repositories_listed":0,"syntology":null},{"url":null,"slug":"stochastic-newton-proximal-extragradient","title":"Stochastic Newton Proximal Extragradient Method","date":"2024-06-03","arxiv_id":"2406.01478","repositories_listed":0,"syntology":null},{"url":null,"slug":"kronecker-factored-approximate-curvature-for-1","title":"Kronecker-Factored Approximate Curvature for Physics-Informed Neural Networks","date":"2024-05-24","arxiv_id":"2405.15603","repositories_listed":0,"syntology":null},{"url":null,"slug":"inverse-free-fast-natural-gradient-descent","title":"Inverse-Free Fast Natural Gradient Descent Method for Deep Learning","date":"2024-03-06","arxiv_id":"2403.03473","repositories_listed":0,"syntology":null},{"url":null,"slug":"second-order-methods-for-bandit-optimization","title":"Second Order Methods for Bandit Optimization and Control","date":"2024-02-14","arxiv_id":"2402.08929","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-challenges-of-the-nonlinear-regime-for","title":"The Challenges of the Nonlinear Regime for Physics-Informed Neural Networks","date":"2024-02-06","arxiv_id":"2402.03864","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-the-temporal-domain-of-differential","title":"On The Temporal Domain of Differential Equation Inspired Graph Neural Networks","date":"2024-01-20","arxiv_id":"2401.11074","repositories_listed":0,"syntology":null},{"url":null,"slug":"krylov-cubic-regularized-newton-a-subspace","title":"Krylov Cubic Regularized Newton: A Subspace Second-Order Method with Dimension-Free Convergence Rate","date":"2024-01-05","arxiv_id":"2401.03058","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-computationally-efficient-sparsified-online","title":"A Computationally Efficient Sparsified Online Newton Method","date":"2023-11-16","arxiv_id":"2311.10085","repositories_listed":0,"syntology":null},{"url":null,"slug":"adaptive-optimization-algorithms-for-machine","title":"Adaptive Optimization Algorithms for Machine Learning","date":"2023-11-16","arxiv_id":"2311.10203","repositories_listed":0,"syntology":null},{"url":null,"slug":"jorge-approximate-preconditioning-for-gpu","title":"Jorge: Approximate Preconditioning for GPU-efficient Second-order Optimization","date":"2023-10-18","arxiv_id":"2310.12298","repositories_listed":0,"syntology":null},{"url":null,"slug":"stochastic-optimization-for-non-convex","title":"Stochastic Optimization for Non-convex Problem with Inexact Hessian Matrix, Gradient, and Function","date":"2023-10-18","arxiv_id":"2310.11866","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-homogenization-approach-for-gradient","title":"A Homogenization Approach for Gradient-Dominated Stochastic Optimization","date":"2023-08-21","arxiv_id":"2308.10630","repositories_listed":0,"syntology":null},{"url":null,"slug":"decentralized-riemannian-conjugate-gradient","title":"Decentralized Riemannian Conjugate Gradient Method on the Stiefel Manifold","date":"2023-08-21","arxiv_id":"2308.10547","repositories_listed":0,"syntology":null},{"url":null,"slug":"convolutions-through-the-lens-of-tensor","title":"Convolutions and More as Einsum: A Tensor Network Perspective with Advances for Second-Order Methods","date":"2023-07-05","arxiv_id":"2307.02275","repositories_listed":0,"syntology":null},{"url":null,"slug":"near-optimal-fully-first-order-algorithms-for","title":"Near-Optimal Nonconvex-Strongly-Convex Bilevel Optimization with Fully First-Order Oracles","date":"2023-06-26","arxiv_id":"2306.14853","repositories_listed":0,"syntology":null},{"url":null,"slug":"minibatching-offers-improved-generalization","title":"Minibatching Offers Improved Generalization Performance for Second Order Optimizers","date":"2023-05-26","arxiv_id":"2307.11684","repositories_listed":0,"syntology":null},{"url":null,"slug":"faster-differentially-private-convex","title":"Faster Differentially Private Convex Optimization via Second-Order Methods","date":"2023-05-22","arxiv_id":"2305.13209","repositories_listed":0,"syntology":null},{"url":null,"slug":"adaptive-consensus-optimization-method-for","title":"Adaptive Consensus Optimization Method for GANs","date":"2023-04-20","arxiv_id":"2304.10317","repositories_listed":0,"syntology":null},{"url":null,"slug":"gradient-boosted-based-structured-and","title":"Gradient-Boosted Based Structured and Unstructured Learning","date":"2023-02-28","arxiv_id":"2302.14299","repositories_listed":0,"syntology":null},{"url":null,"slug":"stochastic-dimension-reduced-second-order","title":"Stochastic Dimension-reduced Second-order Methods for Policy Optimization","date":"2023-01-28","arxiv_id":"2301.12174","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-backpropagating-hessians-through-odes","title":"On backpropagating Hessians through ODEs","date":"2023-01-19","arxiv_id":"2301.08085","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-survey-of-deep-learning-optimizers-first","title":"A survey of deep learning optimizers -- first and second order methods","date":"2022-11-28","arxiv_id":"2211.15596","repositories_listed":0,"syntology":null},{"url":null,"slug":"extra-newton-a-first-approach-to-noise","title":"Extra-Newton: A First Approach to Noise-Adaptive Accelerated Second-Order Methods","date":"2022-11-03","arxiv_id":"2211.01832","repositories_listed":0,"syntology":null},{"url":null,"slug":"explicit-second-order-min-max-optimization","title":"Explicit Second-Order Min-Max Optimization Methods with Optimal Convergence Guarantee","date":"2022-10-23","arxiv_id":"2210.12860","repositories_listed":0,"syntology":null},{"url":null,"slug":"component-wise-natural-gradient-descent-an","title":"Component-Wise Natural Gradient Descent -- An Efficient Neural Network Optimization","date":"2022-10-11","arxiv_id":"2210.05268","repositories_listed":0,"syntology":null},{"url":null,"slug":"mirror-prox-algorithm-for-large-scale-cell","title":"Mirror Prox Algorithm for Large-Scale Cell-Free Massive MIMO Uplink Power Control","date":"2022-09-20","arxiv_id":"2209.09594","repositories_listed":0,"syntology":null},{"url":null,"slug":"adaptive-second-order-coresets-for-data","title":"Adaptive Second Order Coresets for Data-efficient Machine Learning","date":"2022-07-28","arxiv_id":"2207.13887","repositories_listed":0,"syntology":null},{"url":null,"slug":"sp2-a-second-order-stochastic-polyak-method","title":"SP2: A Second Order Stochastic Polyak Method","date":"2022-07-17","arxiv_id":"2207.08171","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-newton-cg-based-barrier-method-for-finding","title":"A Newton-CG based barrier method for finding a second-order stationary point of nonconvex conic optimization with complexity guarantees","date":"2022-07-12","arxiv_id":"2207.05697","repositories_listed":0,"syntology":null},{"url":null,"slug":"stochastic-second-order-methods-provably-beat","title":"Stochastic Second-Order Methods Improve Best-Known Sample Complexity of SGD for Gradient-Dominated Function","date":"2022-05-25","arxiv_id":"2205.12856","repositories_listed":0,"syntology":null}],"syntology_records":15,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"since_archive_judged":{"papers":0,"papers_placed":0,"judged_by":{"model":"a model","models_as_recorded":[],"from":"lb_rows_run_verified.jsonl: each record's `model` field (the extractor's call that wrote decisions[])"},"note":"a model's judgement from the paper's own tables that they report on this leaderboard, not a result: no value from a paper that was not placed is printed or carried here; papers counts each paper once over these leaderboards","backfill":"8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read)","backfill_complete":false,"leaderboards":[]},"papers_where_code_ran":12,"papers_where_code_ran_first_page":"/task/second-order-methods/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not run it on this task or check it against the task's benchmarks.","pages":[{"order":"archive","page":2,"of":2,"url":"/task/second-order-methods/papers/2","json":"/task/second-order-methods/papers/2.json","rows":81},{"order":"ran","page":1,"of":1,"url":"/task/second-order-methods/papers/ran/1","json":"/task/second-order-methods/papers/ran/1.json","rows":12}],"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-10-05T00:36:11+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"row_route":"each syntology object on a benchmark's first row and on a paper carries sample_list (this site's paper page, #ran), syntology_url (syntology.ai's page for the paper, only when that route probed live) and mcp (the agent call that lists the paper's harvested samples; not a verdict on the paper)","developers":"https://syntology.ai/developers"},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"},"record_sha256":"b1e770d5a4f0d0fff5f3ceeb791ff0c1ddf9666260c2a5a271c80efc665c5f28","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}