{"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/amsgrad","slug":"amsgrad","name":"AMSGrad","full_name":"AMSGrad","full_name_withheld":false,"description_markdown":"**AMSGrad** is a stochastic optimization method that seeks to fix a convergence issue with [Adam](https://paperswithcode.com/method/adam) based optimizers. AMSGrad uses the maximum of past squared gradients \r\n$v\\_{t}$ rather than the exponential average to update the parameters:\r\n\r\n$$m\\_{t} = \\beta\\_{1}m\\_{t-1} + \\left(1-\\beta\\_{1}\\right)g\\_{t} $$\r\n\r\n$$v\\_{t} = \\beta\\_{2}v\\_{t-1} + \\left(1-\\beta\\_{2}\\right)g\\_{t}^{2}$$\r\n\r\n$$ \\hat{v}\\_{t} = \\max\\left(\\hat{v}\\_{t-1}, v\\_{t}\\right) $$\r\n\r\n$$\\theta\\_{t+1} = \\theta\\_{t} - \\frac{\\eta}{\\sqrt{\\hat{v}_{t}} + \\epsilon}m\\_{t}$$","description_state":"present","introduced_year":null,"introduced_by":{"title":"On the Convergence of Adam and Beyond","paper":"/paper/on-the-convergence-of-adam-and-beyond-1","first_author":"Sashank J. Reddi","n_authors":3,"url_abs":null,"archive_paper_url":"https://paperswithcode.com/paper/on-the-convergence-of-adam-and-beyond-1"},"source":{"url":"http://arxiv.org/abs/1904.09237v1","title":"On the Convergence of Adam and Beyond","url_on_a_paper_host":true},"code_snippet_url":"https://github.com/pytorch/pytorch/blob/b7bda236d18815052378c88081f64935427d7716/torch/optim/adam.py#L6","code_snippet_url_on_a_code_host":true,"categories":[{"area":"General","area_id":"general","collection":"Stochastic Optimization","url":"/methods/category/stochastic-optimization","pwc_aliases":[]}],"n_papers_tagged":49,"archive_num_papers":49,"papers_newest_first":[{"paper":null,"slug":"non-convergence-to-global-minimizers-in-data","title":"Non-convergence to global minimizers in data driven supervised deep learning: Adam and stochastic gradient descent optimization provably fail to converge to global minimizers in the training of deep neural networks with ReLU activation","date":"2024-10-14","arxiv_id":"2410.10533","n_code_links":0,"syntology":null},{"paper":"/paper/microadam-accurate-adaptive-optimization-with","slug":"microadam-accurate-adaptive-optimization-with","title":"MicroAdam: Accurate Adaptive Optimization with Low Space Overhead and Provable Convergence","date":"2024-05-24","arxiv_id":"2405.15593","n_code_links":1,"syntology":{"ran":7,"of":10,"n_ran_checked":4,"n_instrument":3,"unverified":3,"pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 1 violated, 3 with no contract checked; 3 where Syntology's instrument failed) · 3 unverified","official":{"repos":["ist-daslab/microadam"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"mada-meta-adaptive-optimizers-through-hyper","title":"MADA: Meta-Adaptive Optimizers through hyper-gradient Descent","date":"2024-01-17","arxiv_id":"2401.08893","n_code_links":0,"syntology":null},{"paper":null,"slug":"fedlalr-client-specific-adaptive-learning","title":"FedLALR: Client-Specific Adaptive Learning Rates Achieve Linear Speedup for Non-IID Data","date":"2023-09-18","arxiv_id":"2309.09719","n_code_links":0,"syntology":null},{"paper":null,"slug":"two-sides-of-one-coin-the-limits-of-untuned","title":"Two Sides of One Coin: the Limits of Untuned SGD and the Power of Adaptive Methods","date":"2023-05-21","arxiv_id":"2305.12475","n_code_links":0,"syntology":null},{"paper":null,"slug":"uadam-unified-adam-type-algorithmic-framework","title":"UAdam: Unified Adam-Type Algorithmic Framework for Non-Convex Stochastic Optimization","date":"2023-05-09","arxiv_id":"2305.05675","n_code_links":0,"syntology":null},{"paper":null,"slug":"mathcal-c-k-continuous-spline-approximation","title":"$\\mathcal{C}^k$-continuous Spline Approximation with TensorFlow Gradient Descent Optimizers","date":"2023-03-22","arxiv_id":"2303.12454","n_code_links":0,"syntology":null},{"paper":null,"slug":"adasam-boosting-sharpness-aware-minimization","title":"AdaSAM: Boosting Sharpness-Aware Minimization with Adaptive Learning Rate and Momentum for Training Deep Neural Networks","date":"2023-03-01","arxiv_id":"2303.00565","n_code_links":0,"syntology":null},{"paper":null,"slug":"optimization-methods-in-deep-learning-a","title":"Optimization Methods in Deep Learning: A Comprehensive Overview","date":"2023-02-19","arxiv_id":"2302.09566","n_code_links":0,"syntology":null},{"paper":"/paper/langevin-dynamics-based-algorithm-e-th","slug":"langevin-dynamics-based-algorithm-e-th","title":"Langevin dynamics based algorithm e-TH$\\varepsilon$O POULA for stochastic optimization problems with discontinuous stochastic gradient","date":"2022-10-24","arxiv_id":"2210.13193","n_code_links":1,"syntology":null},{"paper":null,"slug":"communication-efficient-adam-type-algorithms","title":"Communication-Efficient Adam-Type Algorithms for Distributed Data Mining","date":"2022-10-14","arxiv_id":"2210.07454","n_code_links":0,"syntology":null},{"paper":null,"slug":"nest-your-adaptive-algorithm-for-parameter","title":"Nest Your Adaptive Algorithm for Parameter-Agnostic Nonconvex Minimax Optimization","date":"2022-06-01","arxiv_id":"2206.00743","n_code_links":0,"syntology":null},{"paper":null,"slug":"on-distributed-adaptive-optimization-with-1","title":"On Distributed Adaptive Optimization with Gradient Compression","date":"2022-05-11","arxiv_id":"2205.05632","n_code_links":0,"syntology":null},{"paper":"/paper/adaterm-adaptive-t-distribution-estimated","slug":"adaterm-adaptive-t-distribution-estimated","title":"AdaTerm: Adaptive T-Distribution Estimated Robust Moments for Noise-Robust Stochastic Gradient Optimization","date":"2022-01-18","arxiv_id":"2201.06714","n_code_links":1,"syntology":null},{"paper":"/paper/convergence-and-complexity-of-stochastic","slug":"convergence-and-complexity-of-stochastic","title":"Stochastic regularized majorization-minimization with weakly convex and multi-convex surrogates","date":"2022-01-05","arxiv_id":"2201.01652","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-novel-convergence-analysis-for-algorithms","title":"A Novel Convergence Analysis for Algorithms of the Adam Family","date":"2021-12-07","arxiv_id":"2112.03459","n_code_links":0,"syntology":null},{"paper":null,"slug":"convergence-of-adaptive-algorithms-for","title":"Convergence of adaptive algorithms for constrained weakly convex optimization","date":"2021-12-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"communication-compressed-adaptive-gradient","title":"Communication-Compressed Adaptive Gradient Method for Distributed Nonconvex Optimization","date":"2021-11-01","arxiv_id":"2111.00705","n_code_links":0,"syntology":null},{"paper":null,"slug":"sgd-can-converge-to-local-maxima","title":"SGD Can Converge to Local Maxima","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"on-the-convergence-of-decentralized-adaptive","title":"On the Convergence of Decentralized Adaptive Gradient Methods","date":"2021-09-07","arxiv_id":"2109.03194","n_code_links":0,"syntology":null},{"paper":"/paper/adaptive-optimizers-with-sparse-group-lasso-1","slug":"adaptive-optimizers-with-sparse-group-lasso-1","title":"Adaptive Optimizers with Sparse Group Lasso for Neural Networks in CTR Prediction","date":"2021-07-30","arxiv_id":"2107.14432","n_code_links":2,"syntology":null},{"paper":null,"slug":"sgd-may-never-escape-saddle-points","title":"SGD with a Constant Large Learning Rate Can Converge to Local Maxima","date":"2021-07-25","arxiv_id":"2107.11774","n_code_links":0,"syntology":null},{"paper":"/paper/non-asymptotic-estimates-for-tusla-algorithm","slug":"non-asymptotic-estimates-for-tusla-algorithm","title":"Non-asymptotic estimates for TUSLA algorithm for non-convex learning with applications to neural networks with ReLU activation function","date":"2021-07-19","arxiv_id":"2107.08649","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-new-adaptive-gradient-method-with-gradient","title":"A New Adaptive Gradient Method with Gradient Decomposition","date":"2021-07-18","arxiv_id":"2107.08377","n_code_links":0,"syntology":null},{"paper":"/paper/decreasing-scaling-transition-from-adaptive","slug":"decreasing-scaling-transition-from-adaptive","title":"A decreasing scaling transition scheme from Adam to SGD","date":"2021-06-12","arxiv_id":"2106.06749","n_code_links":2,"syntology":null},{"paper":null,"slug":"escaping-saddle-points-faster-with-stochastic-1","title":"Escaping Saddle Points Faster with Stochastic Momentum","date":"2021-06-05","arxiv_id":"2106.02985","n_code_links":0,"syntology":null},{"paper":null,"slug":"on-stochastic-moving-average-estimators-for","title":"Unified Convergence Analysis for Adaptive Optimization with Moving Average Estimator","date":"2021-04-30","arxiv_id":"2104.14840","n_code_links":0,"syntology":null},{"paper":null,"slug":"optimizing-convergence-for-iterative-learning","title":"Optimizing Convergence for Iterative Learning of ARIMA for Stationary Time Series","date":"2021-01-25","arxiv_id":"2101.10037","n_code_links":0,"syntology":null},{"paper":null,"slug":"adam-revisited-a-weighted-past-gradients","title":"Adam revisited: a weighted past gradients perspective","date":"2021-01-01","arxiv_id":"2101.00238","n_code_links":0,"syntology":null},{"paper":null,"slug":"adaptive-optimizers-with-sparse-group-lasso","title":"Adaptive Optimizers with Sparse Group Lasso","date":"2021-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"on-the-marginal-regret-bound-minimization-of","title":"On the Marginal Regret Bound Minimization of Adaptive Methods","date":"2021-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/cada-communication-adaptive-distributed-adam","slug":"cada-communication-adaptive-distributed-adam","title":"CADA: Communication-Adaptive Distributed Adam","date":"2020-12-31","arxiv_id":"2012.15469","n_code_links":1,"syntology":{"ran":0,"of":1,"n_ran_checked":0,"n_instrument":0,"unverified":1,"pointer_only":1,"phrase":"0 ran · 1 unverified","official":null}},{"paper":null,"slug":"bamsprod-a-step-towards-generalizing-the","title":"BAMSProd: A Step towards Generalizing the Adaptive Optimization Methods to Deep Binary Model","date":"2020-09-29","arxiv_id":"2009.13799","n_code_links":0,"syntology":null},{"paper":null,"slug":"towards-deep-robot-learning-with-optimizer","title":"Towards Deep Robot Learning with Optimizer applicable to Non-stationary Problems","date":"2020-07-31","arxiv_id":"2007.15890","n_code_links":0,"syntology":null},{"paper":null,"slug":"analysis-of-q-learning-with-adaptation-and","title":"Analysis of Q-learning with Adaptation and Momentum Restart for Gradient Descent","date":"2020-07-15","arxiv_id":"2007.07422","n_code_links":0,"syntology":null},{"paper":"/paper/adaptive-learning-rates-with-maximum","slug":"adaptive-learning-rates-with-maximum","title":"MaxVA: Fast Adaptation of Step Sizes by Maximizing Observed Variance of Gradients","date":"2020-06-21","arxiv_id":"2006.11918","n_code_links":1,"syntology":null},{"paper":"/paper/adaptive-gradient-methods-converge-faster","slug":"adaptive-gradient-methods-converge-faster","title":"Adaptive Gradient Methods Converge Faster with Over-Parameterization (but you should do a line-search)","date":"2020-06-11","arxiv_id":"2006.06835","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":1,"n_instrument":1,"unverified":0,"pointer_only":2,"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) · 0 unverified","official":null}},{"paper":null,"slug":"convergence-of-adaptive-algorithms-for-weakly","title":"Convergence of adaptive algorithms for weakly convex constrained optimization","date":"2020-06-11","arxiv_id":"2006.06650","n_code_links":0,"syntology":null},{"paper":null,"slug":"mixml-a-unified-analysis-of-weakly-consistent","title":"MixML: A Unified Analysis of Weakly Consistent Parallel Learning","date":"2020-05-14","arxiv_id":"2005.06706","n_code_links":0,"syntology":null},{"paper":null,"slug":"non-asymptotic-convergence-of-adam-type","title":"Non-asymptotic Convergence of Adam-type Reinforcement Learning Algorithms under Markovian Sampling","date":"2020-02-15","arxiv_id":"2002.06286","n_code_links":0,"syntology":null},{"paper":null,"slug":"adamt-a-stochastic-optimization-with-trend-1","title":"On the Trend-corrected Variant of Adaptive Stochastic Optimization Methods","date":"2020-01-17","arxiv_id":"2001.06130","n_code_links":0,"syntology":null},{"paper":"/paper/an-adaptive-and-momental-bound-method-for","slug":"an-adaptive-and-momental-bound-method-for","title":"An Adaptive and Momental Bound Method for Stochastic Learning","date":"2019-10-27","arxiv_id":"1910.12249","n_code_links":2,"syntology":{"ran":2,"of":2,"n_ran_checked":2,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["lancopku/AdaMod"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/diffgrad-an-optimization-method-for","slug":"diffgrad-an-optimization-method-for","title":"diffGrad: An Optimization Method for Convolutional Neural Networks","date":"2019-09-12","arxiv_id":"1909.11015","n_code_links":1,"syntology":null},{"paper":null,"slug":"meta-descent-for-online-continual-prediction","title":"Meta-descent for Online, Continual Prediction","date":"2019-07-17","arxiv_id":"1907.07751","n_code_links":0,"syntology":null},{"paper":null,"slug":"power-gradient-descent","title":"Power Gradient Descent","date":"2019-06-11","arxiv_id":"1906.04787","n_code_links":0,"syntology":null},{"paper":"/paper/190600195","slug":"190600195","title":"Multivariate, Multistep Forecasting, Reconstruction and Feature Selection of Ocean Waves via Recurrent and Sequence-to-Sequence Networks","date":"2019-06-01","arxiv_id":"1906.00195","n_code_links":1,"syntology":null},{"paper":null,"slug":"accelerating-first-order-optimization","title":"Accelerating first order optimization algorithms","date":"2019-05-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"optimistic-acceleration-for-optimization","title":"Optimistic Acceleration for Optimization","date":"2019-05-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/on-the-convergence-of-adam-and-beyond-1","slug":"on-the-convergence-of-adam-and-beyond-1","title":"On the Convergence of Adam and Beyond","date":"2019-04-19","arxiv_id":"1904.09237","n_code_links":3,"syntology":{"ran":2,"of":2,"n_ran_checked":2,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":null}}],"papers_shown":49,"papers_order":"date (newest first), then slug","paper_counts":{"archive_papers_tagged":49,"with_a_code_link":14,"where_syntology_ran_a_sample":4,"not_listed_spam_title":0,"listed":49,"listed_where_code_ran":4,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":4,"every_run_a_failure_of_syntologys_instrument":0,"listed_with_a_run_with_no_instrument_failure":4,"listed_every_run_a_failure_of_syntologys_instrument":0,"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":4,"papers_where_code_ran_first_page":"/method/amsgrad/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":"ran","page":1,"of":1,"url":"/method/amsgrad/papers/ran/1","json":"/method/amsgrad/papers/ran/1.json","rows":4}],"tasks":[{"task":"/task/stochastic-optimization","name":"Stochastic Optimization","papers":12},{"task":"/task/deep-learning","name":"Deep Learning","papers":3},{"task":"/task/distributed-optimization","name":"Distributed Optimization","papers":3},{"task":"/task/machine-learning","name":"BIG-bench Machine Learning","papers":2},{"task":"/task/bilevel-optimization","name":"Bilevel Optimization","papers":2},{"task":"/task/open-question","name":"Open-Ended Question Answering","papers":2},{"task":"/task/quantization","name":"Quantization","papers":2},{"task":"/task/scheduling","name":"Scheduling","papers":2},{"task":"/task/time-series-1","name":"Time Series","papers":2},{"task":"/task/time-series","name":"Time Series Analysis","papers":2},{"task":"/task/transfer-learning","name":"Transfer Learning","papers":2},{"task":"/task/type","name":"Vocal Bursts Type Prediction","papers":2},{"task":"/task/atari-games","name":"Atari Games","papers":1},{"task":"/task/binary-classification","name":"Binary Classification","papers":1},{"task":"/task/click-through-rate-prediction","name":"Click-Through Rate Prediction","papers":1},{"task":"/task/computational-efficiency","name":"Computational Efficiency","papers":1},{"task":"/task/dictionary-learning","name":"Dictionary Learning","papers":1},{"task":"/task/distributed-computing","name":"Distributed Computing","papers":1},{"task":"/task/federated-learning","name":"Federated Learning","papers":1},{"task":"/task/hyperparameter-optimization","name":"Hyperparameter Optimization","papers":1}],"tasks_shown":20,"n_tasks":39,"usage_by_year":[{"year":"2019","papers":8},{"year":"2020","papers":10},{"year":"2021","papers":16},{"year":"2022","papers":6},{"year":"2023","papers":6},{"year":"2024","papers":3}],"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/amsgrad"},"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=AMSGrad","read_at":"2026-10-05T00:52:18+00:00","query":"AMSGrad","kind":"method","have":"unknown_name","tier":null,"verified_implementation":null,"level":null,"level_meaning":"the served verification level, per answer; never summed across methods","resolved_to":null,"resolution":null,"resolved_name_differs":false,"absence_asserted":false,"absence_unchecked":null,"no_code_is_about_this_method":false,"subject":null,"archive_paper_arxiv_id":"1904.09237","repositories":null,"retrieve_with":null,"name_competition":{"verdict":"none","may_be_wrong_sense":false,"bearers_found":0,"served":null,"leading_other_bearer":null,"n_other_bearers_listed":0,"note":"Nothing in this corpus is named 'AMSGrad' -- no method node, no paper announcing it in its title, no expanded form declaring it as an acronym."},"name_competition_text":null,"near_matches":["Q-AMSGrad"],"code_nearby":[],"code_nearby_caption":null,"origin_paper":null,"line":"name not resolved (unknown_name). The lookup matched no method, paper or venue by this name; that asserts nothing about whether code exists.","level_legend":null},"syntology_have_state":"loaded","record_sha256":"f81e90128e88c6b87244ea690a5f4590cacf3b0b10dcf225daaf0e27a4446fde","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}