{"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 (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":30,"of":52,"tagged_in_all":181,"items":[{"url":"/paper/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":1,"n_unverified":10,"n_pointer_only":0}},{"url":"/paper/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","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_unverified":1,"n_pointer_only":9}},{"url":"/paper/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_unverified":0,"n_pointer_only":1}},{"url":"/paper/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","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_unverified":7,"n_pointer_only":0}},{"url":"/paper/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","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","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","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","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","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_unverified":0,"n_pointer_only":3}},{"url":"/paper/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","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":0,"n_unverified":3,"n_pointer_only":0}},{"url":"/paper/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","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","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","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","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","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","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_unverified":9,"n_pointer_only":16}},{"url":"/paper/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_unverified":1,"n_pointer_only":0}},{"url":"/paper/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_unverified":1,"n_pointer_only":10}},{"url":"/paper/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","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_unverified":1,"n_pointer_only":0}},{"url":"/paper/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_unverified":0,"n_pointer_only":1}},{"url":"/paper/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_unverified":1,"n_pointer_only":0}},{"url":"/paper/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","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","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}],"syntology_records":12,"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"},"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":"2026-09-24T18:15:14+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; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"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"}}