{"list":"other","total":53,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1910.10683","title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","created":"2019-10-23","cited_by_count":14599},{"id":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"id":"2203.15556","title":"Training Compute-Optimal Large Language Models","created":"2022-03-29","cited_by_count":3019},{"id":"1904.09237","title":"On the Convergence of Adam and Beyond","created":"2019-04-19","cited_by_count":841},{"id":"1908.03265","title":"On the Variance of the Adaptive Learning Rate and Beyond","created":"2019-08-08","cited_by_count":772},{"id":"1608.04636","title":"Linear Convergence of Gradient and Proximal-Gradient Methods Under the Polyak-\\L{}ojasiewicz Condition","created":"2016-08-16","cited_by_count":539},{"id":"2302.06675","title":"Symbolic Discovery of Optimization Algorithms","created":"2023-02-13","cited_by_count":434},{"id":"2502.16982","title":"Muon is Scalable for LLM Training","created":"2025-02-24","cited_by_count":428},{"id":"2103.00065","title":"Gradient Descent on Neural Networks Typically Occurs at the Edge of Stability","created":"2021-02-26","cited_by_count":427},{"id":"1802.09568","title":"Shampoo: Preconditioned Stochastic Tensor Optimization","created":"2018-02-26","cited_by_count":426},{"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":"2010.07468","title":"AdaBelief Optimizer: Adapting Stepsizes by the Belief in Observed Gradients","created":"2020-10-15","cited_by_count":283},{"id":"2305.14342","title":"Sophia: A Scalable Stochastic Second-order Optimizer for Language Model Pre-training","created":"2023-05-23","cited_by_count":265},{"id":"2409.20325","title":"Old Optimizer, New Norm: An Anthology","created":"2024-09-30","cited_by_count":193},{"id":"2502.07529","title":"Training Deep Learning Models with Norm-Constrained LMOs","created":"2025-02-11","cited_by_count":192},{"id":"1902.09843","title":"Adaptive Gradient Methods with Dynamic Bound of Learning Rate","created":"2019-02-26","cited_by_count":183},{"id":"1806.01811","title":"AdaGrad stepsizes: Sharp convergence over nonconvex landscapes","created":"2018-06-05","cited_by_count":182},{"id":"1808.02941","title":"On the Convergence of A Class of Adam-Type Algorithms for Non-Convex Optimization","created":"2018-08-08","cited_by_count":174},{"id":"2208.06677","title":"Adan: Adaptive Nesterov Momentum Algorithm for Faster Optimizing Deep Models","created":"2022-08-13","cited_by_count":174},{"id":"2002.03305","title":"Momentum Improves Normalized SGD","created":"2020-02-09","cited_by_count":139},{"id":"2304.13972","title":"Convergence of Adam Under Relaxed Assumptions","created":"2023-04-27","cited_by_count":99},{"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":"1808.05671","title":"On the Convergence of Adaptive Gradient Methods for Nonconvex Optimization","created":"2018-08-16","cited_by_count":91},{"id":"2506.15054","title":"Muon Optimizes Under Spectral Norm Constraints","created":"2025-06-18","cited_by_count":86},{"id":"2502.02900","title":"A Note on the Convergence of Muon","created":"2025-02-05","cited_by_count":83},{"id":"2106.14343","title":"High-probability Bounds for Non-Convex Stochastic Optimization with Heavy Tails","created":"2021-06-28","cited_by_count":80},{"id":"2505.02222","title":"Practical Efficiency of Muon for Pretraining","created":"2025-05-04","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":"2507.11005","title":"AdaMuon: Adaptive Muon Optimizer","created":"2025-07-15","cited_by_count":67},{"id":"2411.10438","title":"MARS: Unleashing the Power of Variance Reduction for Training Large Models","created":"2024-11-15","cited_by_count":64},{"id":"1806.07811","title":"Stochastic Nested Variance Reduction for Nonconvex Optimization","created":"2018-06-20","cited_by_count":63},{"id":"2503.20762","title":"ASGO: Adaptive Structured Gradient Optimization","created":"2025-03-26","cited_by_count":57},{"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":"2112.03459","title":"A Novel Convergence Analysis for Algorithms of the Adam Family","created":"2021-12-07","cited_by_count":50},{"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":"2502.04664","title":"Implicit Bias of Spectral Descent and Muon on Multiclass Separable Data","created":"2025-02-07","cited_by_count":41},{"id":"2506.04192","title":"Lions and Muons: Optimization via Stochastic Frank-Wolfe under Heavy-Tailed Noise","created":"2025-06-04","cited_by_count":41},{"id":"2006.15815","title":"Adaptive Inertia: Disentangling the Effects of Adaptive Learning Rate and Momentum","created":"2020-06-29","cited_by_count":40},{"id":"2106.08208","title":"SUPER-ADAM: Faster and Universal Framework of Adaptive Gradients","created":"2021-06-15","cited_by_count":40},{"id":"1803.00225","title":"Global Convergence of Block Coordinate Descent in Deep Learning","created":"2018-03-01","cited_by_count":38},{"id":"2310.17998","title":"Closing the Gap Between the Upper Bound and the Lower Bound of Adam's Iteration Complexity","created":"2023-10-27","cited_by_count":38},{"id":"2502.17410","title":"COSMOS: A Hybrid Adaptive Optimizer for Memory-Efficient Training of LLMs","created":"2025-02-24","cited_by_count":30},{"id":"1908.10525","title":"Linear Convergence of Adaptive Stochastic Gradient Descent","created":"2019-08-28","cited_by_count":29},{"id":"2507.01598","title":"Convergence Bound and Critical Batch Size of Muon Optimizer","created":"2025-07-02","cited_by_count":28},{"id":"2305.12475","title":"Two Sides of One Coin: the Limits of Untuned SGD and the Power of Adaptive Methods","created":"2023-05-21","cited_by_count":23},{"id":"2509.02981","title":"AdaGrad Meets Muon: Adaptive Stepsizes for Orthogonal Updates","created":"2025-09-03","cited_by_count":23},{"id":"2509.14562","title":"LiMuon: Light and Fast Muon Optimizer for Large Models","created":"2025-09-18","cited_by_count":22},{"id":"2307.11782","title":"Convergence of Adam for Non-convex Objectives: Relaxed Hyperparameters and Non-ergodic Case","created":"2023-07-20","cited_by_count":14},{"id":"2208.10025","title":"Simple and Optimal Stochastic Gradient Methods for Nonsmooth Nonconvex Optimization","created":"2022-08-22","cited_by_count":5}],"next_cursor":null}