{"list":"other","total":77,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1802.04434","title":"signSGD: Compressed Optimisation for Non-Convex Problems","created":"2018-02-13","cited_by_count":571},{"id":"2302.06675","title":"Symbolic Discovery of Optimization Algorithms","created":"2023-02-13","cited_by_count":434},{"id":"1802.09568","title":"Shampoo: Preconditioned Stochastic Tensor Optimization","created":"2018-02-26","cited_by_count":426},{"id":"1901.09847","title":"Error Feedback Fixes SignSGD and other Gradient Compression Schemes","created":"2019-01-28","cited_by_count":310},{"id":"1912.02365","title":"Lower Bounds for Non-Convex Stochastic Optimization","created":"2019-12-05","cited_by_count":307},{"id":"1905.10018","title":"Momentum-Based Variance Reduction in Non-Convex SGD","created":"2019-05-24","cited_by_count":306},{"id":"1807.01695","title":"SPIDER: Near-Optimal Non-Convex Optimization via Stochastic Path Integrated Differential Estimator","created":"2018-07-04","cited_by_count":287},{"id":"2409.11321","title":"SOAP: Improving and Stabilizing Shampoo using Adam","created":"2024-09-17","cited_by_count":192},{"id":"2502.07529","title":"Training Deep Learning Models with Norm-Constrained LMOs","created":"2025-02-11","cited_by_count":192},{"id":"2006.04740","title":"The Heavy-Tail Phenomenon in SGD","created":"2020-06-08","cited_by_count":124},{"id":"2008.10898","title":"PAGE: A Simple and Optimal Probabilistic Gradient Estimator for Nonconvex Optimization","created":"2020-08-25","cited_by_count":119},{"id":"2304.13960","title":"Noise Is Not the Main Factor Behind the Gap Between SGD and Adam on Transformers, but Sign Descent Might Be","created":"2023-04-27","cited_by_count":114},{"id":"2005.10785","title":"Stochastic Optimization with Heavy-Tailed Noise via Accelerated Gradient Clipping","created":"2020-05-21","cited_by_count":104},{"id":"2310.01082","title":"Linear attention is (maybe) all you need (to understand transformer optimization)","created":"2023-10-02","cited_by_count":98},{"id":"2503.12645","title":"Understanding Gradient Orthogonalization for Deep Learning via Non-Euclidean Trust-Region Optimization","created":"2025-03-16","cited_by_count":92},{"id":"2502.02900","title":"A Note on the Convergence of Muon","created":"2025-02-05","cited_by_count":83},{"id":"2208.11195","title":"Robustness to Unbounded Smoothness of Generalized SignSGD","created":"2022-08-23","cited_by_count":81},{"id":"2106.14343","title":"High-probability Bounds for Non-Convex Stochastic Optimization with Heavy Tails","created":"2021-06-28","cited_by_count":80},{"id":"2505.13416","title":"Gluon: Making Muon & Scion Great Again! (Bridging Theory and Practice of LMO-based Optimizers for LLMs)","created":"2025-05-19","cited_by_count":72},{"id":"2411.10438","title":"MARS: Unleashing the Power of Variance Reduction for Training Large Models","created":"2024-11-15","cited_by_count":64},{"id":"1607.00345","title":"Convergence Rate of Frank-Wolfe for Non-Convex Objectives","created":"2016-07-01","cited_by_count":63},{"id":"2302.00999","title":"High-Probability Bounds for Stochastic Optimization and Variational Inequalities: the Case of Unbounded Variance","created":"2023-02-02","cited_by_count":61},{"id":"2406.17748","title":"A New Perspective on Shampoo's Preconditioner","created":"2024-06-25","cited_by_count":59},{"id":"2404.04454","title":"Implicit Bias of AdamW: $\\ell_\\infty$ Norm Constrained Optimization","created":"2024-04-05","cited_by_count":58},{"id":"2305.17212","title":"Rotational Equilibrium: How Weight Decay Balances Learning Across Neural Networks","created":"2023-05-26","cited_by_count":53},{"id":"2505.21799","title":"PolarGrad: A Class of Matrix-Gradient Optimizers from a Unifying Preconditioning Perspective","created":"2025-05-27","cited_by_count":52},{"id":"2310.05898","title":"Lion Secretly Solves Constrained Optimization: As Lyapunov Predicts","created":"2023-10-09","cited_by_count":51},{"id":"1905.12938","title":"Stochastic Sign Descent Methods: New Algorithms and Better Theory","created":"2019-05-30","cited_by_count":49},{"id":"2410.13849","title":"From Gradient Clipping to Normalization for Heavy Tailed SGD","created":"2024-10-17","cited_by_count":49},{"id":"1804.09554","title":"Stochastic Conditional Gradient Methods: From Convex Minimization to Submodular Maximization","created":"2018-04-24","cited_by_count":47},{"id":"2411.16085","title":"Cautious Optimizers: Improving Training with One Line of Code","created":"2024-11-25","cited_by_count":47},{"id":"1406.1305","title":"Faster Rates for the Frank-Wolfe Method over Strongly-Convex Sets","created":"2014-06-05","cited_by_count":44},{"id":"1912.00018","title":"On the Heavy-Tailed Theory of Stochastic Gradient Descent for Deep Neural Networks","created":"2019-11-29","cited_by_count":43},{"id":"2412.19529","title":"Nonconvex Stochastic Optimization under Heavy-Tailed Noises: Optimal Convergence without Gradient Clipping","created":"2024-12-27","cited_by_count":42},{"id":"1607.08254","title":"Stochastic Frank-Wolfe Methods for Nonconvex Optimization","created":"2016-07-27","cited_by_count":41},{"id":"2407.07972","title":"Deconstructing What Makes a Good Optimizer for Language Models","created":"2024-07-10","cited_by_count":41},{"id":"1602.02101","title":"Variance-Reduced and Projection-Free Stochastic Optimization","created":"2016-02-05","cited_by_count":40},{"id":"2408.12857","title":"Memory-Efficient LLM Training with Online Subspace Descent","created":"2024-08-23","cited_by_count":39},{"id":"2102.06489","title":"Stability and Convergence of Stochastic Gradient Clipping: Beyond Lipschitz Continuity and Smoothness","created":"2021-02-12","cited_by_count":37},{"id":"2002.10940","title":"Stochastic-Sign SGD for Federated Learning with Theoretical Guarantees","created":"2020-02-25","cited_by_count":35},{"id":"1905.05920","title":"Hybrid Stochastic Gradient Descent Algorithms for Stochastic Nonconvex Optimization","created":"2019-05-15","cited_by_count":32},{"id":"1910.04322","title":"One Sample Stochastic Frank-Wolfe","created":"2019-10-10","cited_by_count":32},{"id":"2502.17410","title":"COSMOS: A Hybrid Adaptive Optimizer for Memory-Efficient Training of LLMs","created":"2025-02-24","cited_by_count":30},{"id":"1906.01736","title":"Distributed Training with Heterogeneous Data: Bridging Median- and Mean-Based Algorithms","created":"2019-06-04","cited_by_count":29},{"id":"2302.06763","title":"Breaking the Lower Bound with (Little) Structure: Acceleration in Non-Convex Stochastic Optimization with Heavy-Tailed Noise","created":"2023-02-14","cited_by_count":27},{"id":"2310.01860","title":"High-Probability Convergence for Composite and Distributed Stochastic Minimization and Variational Inequalities with Heavy-Tailed Noise","created":"2023-10-03","cited_by_count":24},{"id":"1805.06792","title":"Faster Rates for Convex-Concave Games","created":"2018-05-17","cited_by_count":23},{"id":"2010.07243","title":"Deep Neural Network Training with Frank-Wolfe","created":"2020-10-14","cited_by_count":23},{"id":"2410.23922","title":"Analyzing & Reducing the Need for Learning Rate Warmup in GPT Training","created":"2024-10-31","cited_by_count":22},{"id":"2311.04161","title":"Breaking the Heavy-Tailed Noise Barrier in Stochastic Optimization Problems","created":"2023-11-07","cited_by_count":21},{"id":"2101.10040","title":"Complexity of Linear Minimization and Projection on Some Sets","created":"2021-01-25","cited_by_count":20},{"id":"2111.11309","title":"No-Regret Dynamics in the Fenchel Game: A Unified Framework for Algorithmic Convex Optimization","created":"2021-11-22","cited_by_count":20},{"id":"2404.00438","title":"Communication Efficient Distributed Training with Distributed Lion","created":"2024-03-30","cited_by_count":18},{"id":"2406.04443","title":"Clipping Improves Adam-Norm and AdaGrad-Norm when the Noise Is Heavy-Tailed","created":"2024-06-06","cited_by_count":18},{"id":"2006.06293","title":"Multiplicative noise and heavy tails in stochastic optimization","created":"2020-06-11","cited_by_count":17},{"id":"2211.14103","title":"Conditional Gradient Methods","created":"2022-11-25","cited_by_count":17},{"id":"2002.11860","title":"Stochastic Frank-Wolfe for Constrained Finite-Sum Minimization","created":"2020-02-27","cited_by_count":14},{"id":"2206.01095","title":"Clipped Stochastic Methods for Variational Inequalities with Heavy-Tailed Noise","created":"2022-06-02","cited_by_count":14},{"id":"2304.01119","title":"Improved Convergence in High Probability of Clipped Gradient Methods with Heavy Tails","created":"2023-04-03","cited_by_count":13},{"id":"2406.00489","title":"Efficient Sign-Based Optimization: Accelerating Convergence via Variance Reduction","created":"2024-06-01","cited_by_count":13},{"id":"1708.04783","title":"Non-convex Conditional Gradient Sliding","created":"2017-08-16","cited_by_count":12},{"id":"2411.07724","title":"Convergence Rate Analysis of LION","created":"2024-11-12","cited_by_count":11},{"id":"2302.04859","title":"Projection-free Online Exp-concave Optimization","created":"2023-02-09","cited_by_count":10},{"id":"2310.18763","title":"Accelerated Zeroth-order Method for Non-Smooth Stochastic Convex Optimization Problem with Infinite Variance","created":"2023-10-28","cited_by_count":10},{"id":"1807.07680","title":"Generalized Stochastic Frank-Wolfe Algorithm with Stochastic \"Substitute\" Gradient for Structured Convex Optimization","created":"2018-07-20","cited_by_count":8},{"id":"1902.06992","title":"Stochastic Conditional Gradient++","created":"2019-02-19","cited_by_count":8},{"id":"1912.01467","title":"Linear Convergence of Frank-Wolfe for Rank-One Matrix Recovery Without Strong Convexity","created":"2019-12-03","cited_by_count":7},{"id":"2110.04243","title":"Heavy Ball Momentum for Conditional Gradient","created":"2021-10-08","cited_by_count":7},{"id":"2304.11737","title":"Sarah Frank-Wolfe: Methods for Constrained Optimization with Best Rates and Practical Features","created":"2023-04-23","cited_by_count":7},{"id":"2305.13187","title":"SignSVRG: fixing SignSGD via variance reduction","created":"2023-05-22","cited_by_count":7},{"id":"2011.03351","title":"Affine Invariant Analysis of Frank-Wolfe on Strongly Convex Sets","created":"2020-11-06","cited_by_count":6},{"id":"2307.13680","title":"High Probability Analysis for Non-Convex Stochastic Optimization with Clipping","created":"2023-07-25","cited_by_count":5},{"id":"2406.06788","title":"Stochastic Frank-Wolfe: Unified Analysis and Zoo of Special Cases","created":"2024-06-10","cited_by_count":5},{"id":"2210.00665","title":"Distributed Non-Convex Optimization with One-Bit Compressors on Heterogeneous Data: Efficient and Resilient Algorithms","created":"2022-10-03","cited_by_count":4},{"id":"2501.18773","title":"Beyond Short Steps in Frank-Wolfe Algorithms","created":"2025-01-30","cited_by_count":4},{"id":"2310.15976","title":"Convergence of Sign-based Random Reshuffling Algorithms for Nonconvex Optimization","created":"2023-10-24","cited_by_count":2}],"next_cursor":null}