{"total":87,"rows":[{"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,"area":null},{"id":"2304.13972","title":"Convergence of Adam Under Relaxed Assumptions","created":"2023-04-27","cited_by_count":99,"area":null},{"id":"2305.01588","title":"Revisiting Gradient Clipping: Stochastic bias and tight convergence guarantees","created":"2023-05-02","cited_by_count":83,"area":null},{"id":"2208.11195","title":"Robustness to Unbounded Smoothness of Generalized SignSGD","created":"2022-08-23","cited_by_count":81,"area":null},{"id":"2106.14343","title":"High-probability Bounds for Non-Convex Stochastic Optimization with Heavy Tails","created":"2021-06-28","cited_by_count":80,"area":null},{"id":"2109.14119","title":"Stochastic Training is Not Necessary for Generalization","created":"2021-09-29","cited_by_count":63,"area":null},{"id":"2210.04264","title":"CAGroup3D: Class-Aware Grouping for 3D Object Detection on Point Clouds","created":"2022-10-09","cited_by_count":58,"area":null},{"id":"2305.18471","title":"Convergence of AdaGrad for Non-convex Objectives: Simple Proofs and Relaxed Assumptions","created":"2023-05-29","cited_by_count":57,"area":null},{"id":"2306.01264","title":"Convex and Non-convex Optimization Under Generalized Smoothness","created":"2023-06-02","cited_by_count":44,"area":null},{"id":"2412.19529","title":"Nonconvex Stochastic Optimization under Heavy-Tailed Noises: Optimal Convergence without Gradient Clipping","created":"2024-12-27","cited_by_count":42,"area":null},{"id":"2302.06570","title":"Beyond Uniform Smoothness: A Stopped Analysis of Adaptive SGD","created":"2023-02-13","cited_by_count":41,"area":null},{"id":"2204.02251","title":"RBGNet: Ray-based Grouping for 3D Object Detection","created":"2022-04-05","cited_by_count":40,"area":null},{"id":"2110.12459","title":"Non-convex Distributionally Robust Optimization: Non-asymptotic Analysis","created":"2021-10-24","cited_by_count":39,"area":null},{"id":"2102.06489","title":"Stability and Convergence of Stochastic Gradient Clipping: Beyond Lipschitz Continuity and Smoothness","created":"2021-02-12","cited_by_count":37,"area":null},{"id":"2206.13033","title":"Normalized/Clipped SGD with Perturbation for Differentially Private Non-Convex Optimization","created":"2022-06-27","cited_by_count":36,"area":null},{"id":"2410.20011","title":"A Survey of Small Language Models","created":"2024-10-25","cited_by_count":31,"area":null},{"id":"2208.09900","title":"Provable Adaptivity of Adam under Non-uniform Smoothness","created":"2022-08-21","cited_by_count":30,"area":null},{"id":"2311.03252","title":"Parameter-Agnostic Optimization under Relaxed Smoothness","created":"2023-11-06","cited_by_count":29,"area":null},{"id":"2303.00883","title":"Variance-reduced Clipping for Non-convex Optimization","created":"2023-03-02","cited_by_count":22,"area":null},{"id":"2406.15244","title":"AdaGrad under Anisotropic Smoothness","created":"2024-06-21","cited_by_count":22,"area":null},{"id":"2212.00328","title":"Differentially Private Learning with Per-Sample Adaptive Clipping","created":"2022-12-01","cited_by_count":21,"area":null},{"id":"2402.03982","title":"On Convergence of Adam for Stochastic Optimization under Relaxed Assumptions","created":"2024-02-06","cited_by_count":21,"area":null},{"id":"2205.05040","title":"A Communication-Efficient Distributed Gradient Clipping Algorithm for Training Deep Neural Networks","created":"2022-05-10","cited_by_count":20,"area":null},{"id":"2310.12474","title":"Enhancing High-Resolution 3D Generation through Pixel-wise Gradient Clipping","created":"2023-10-19","cited_by_count":17,"area":null},{"id":"2403.04081","title":"Directional Smoothness and Gradient Methods: Convergence and Adaptivity","created":"2024-03-06","cited_by_count":17,"area":null},{"id":"2506.01913","title":"Generalized Gradient Norm Clipping & Non-Euclidean $(L_0,L_1)$-Smoothness","created":"2025-06-02","cited_by_count":17,"area":null},{"id":"2401.09587","title":"Bilevel Optimization under Unbounded Smoothness: A New Algorithm and Convergence Analysis","created":"2024-01-17","cited_by_count":15,"area":null},{"id":"2402.13794","title":"Revisiting Convergence of AdaGrad with Relaxed Assumptions","created":"2024-02-21","cited_by_count":15,"area":null},{"id":"2311.14632","title":"Differentially Private SGD Without Clipping Bias: An Error-Feedback Approach","created":"2023-11-24","cited_by_count":14,"area":null},{"id":"2403.15146","title":"On the Convergence of Adam under Non-uniform Smoothness: Separability from SGDM and Beyond","created":"2024-03-22","cited_by_count":14,"area":null},{"id":"2404.01436","title":"Convergence Guarantees for RMSProp and Adam in Generalized-smooth Non-convex Optimization with Affine Noise Variance","created":"2024-04-01","cited_by_count":14,"area":null},{"id":"2502.07923","title":"Sign Operator for Coping with Heavy-Tailed Noise in Non-Convex Optimization: High Probability Bounds Under $(L_0, L_1)$-Smoothness","created":"2025-02-11","cited_by_count":13,"area":null},{"id":"2405.14432","title":"Adaptive Gradient Clipping for Robust Federated Learning","created":"2024-05-23","cited_by_count":11,"area":null},{"id":"2408.09074","title":"Gradient-Variation Online Learning under Generalized Smoothness","created":"2024-08-17","cited_by_count":11,"area":null},{"id":"2210.00690","title":"Taming Fat-Tailed (\"Heavier-Tailed'' with Potentially Infinite Variance) Noise in Federated Learning","created":"2022-10-03","cited_by_count":10,"area":null},{"id":"2305.09896","title":"Convergence and Privacy of Decentralized Nonconvex Optimization with Gradient Clipping and Communication Compression","created":"2023-05-17","cited_by_count":9,"area":null},{"id":"2409.19212","title":"An Accelerated Algorithm for Stochastic Bilevel Optimization under Unbounded Smoothness","created":"2024-09-28","cited_by_count":9,"area":null},{"id":"2402.11215","title":"AdAdaGrad: Adaptive Batch Size Schemes for Adaptive Gradient Methods","created":"2024-02-17","cited_by_count":8,"area":null},{"id":"2508.17426","title":"Modular MeanFlow: Towards Stable and Scalable One-Step Generative Modeling","created":"2025-08-24","cited_by_count":8,"area":null},{"id":"2302.07155","title":"EPISODE: Episodic Gradient Clipping with Periodic Resampled Corrections for Federated Learning with Heterogeneous Data","created":"2023-02-14","cited_by_count":7,"area":null},{"id":"2406.11733","title":"To Clip or not to Clip: the Dynamics of SGD with Gradient Clipping in High-Dimensions","created":"2024-06-17","cited_by_count":7,"area":null},{"id":"2410.15637","title":"Large Deviation Upper Bounds and Improved MSE Rates of Nonlinear SGD: Heavy-tailed Noise and Power of Symmetry","created":"2024-10-21","cited_by_count":7,"area":null},{"id":"2412.20017","title":"A Nearly Optimal Single Loop Algorithm for Stochastic Bilevel Optimization under Unbounded Smoothness","created":"2024-12-28","cited_by_count":7,"area":null},{"id":"2502.04164","title":"Efficient Distributed Optimization under Heavy-Tailed Noise","created":"2025-02-06","cited_by_count":7,"area":null},{"id":"2503.16125","title":"Uncertainty Meets Diversity: A Comprehensive Active Learning Framework for Indoor 3D Object Detection","created":"2025-03-20","cited_by_count":7,"area":null},{"id":"2505.16363","title":"AdamS: Momentum Itself Can Be A Normalizer for LLM Pretraining and Post-training","created":"2025-05-22","cited_by_count":6,"area":null},{"id":"2206.04688","title":"A New Frontier of AI: On-Device AI Training and Personalization","created":"2022-06-09","cited_by_count":5,"area":null},{"id":"2307.13680","title":"High Probability Analysis for Non-Convex Stochastic Optimization with Clipping","created":"2023-07-25","cited_by_count":5,"area":null},{"id":"2310.14616","title":"Rethinking SIGN Training: Provable Nonconvex Acceleration without First- and Second-Order Gradient Lipschitz","created":"2023-10-23","cited_by_count":4,"area":null},{"id":"2409.03682","title":"A New First-Order Meta-Learning Algorithm with Convergence Guarantees","created":"2024-09-05","cited_by_count":4,"area":null},{"id":"2410.14054","title":"Adaptive Gradient Normalization and Independent Sampling for (Stochastic) Generalized-Smooth Optimization","created":"2024-10-17","cited_by_count":4,"area":null},{"id":"2410.16871","title":"Error Feedback under $(L_0,L_1)$-Smoothness: Normalization and Momentum","created":"2024-10-22","cited_by_count":4,"area":null},{"id":"2502.17772","title":"An Improved Privacy and Utility Analysis of Differentially Private SGD with Bounded Domain and Smooth Losses","created":"2025-02-25","cited_by_count":4,"area":null},{"id":"2506.00181","title":"On the Interaction of Batch Noise, Adaptivity, and Compression, under $(L_0,L_1)$-Smoothness: An SDE Approach","created":"2025-05-30","cited_by_count":4,"area":null},{"id":"2507.05966","title":"Simple Convergence Proof of Adam From a Sign-like Descent Perspective","created":"2025-07-08","cited_by_count":4,"area":null},{"id":"2509.07972","title":"Theoretical Analysis on how Learning Rate Warmup Accelerates Convergence","created":"2025-09-09","cited_by_count":4,"area":null},{"id":"2307.10053","title":"Stochastic Subgradient Methods with Guaranteed Global Stability in Nonsmooth Nonconvex Optimization","created":"2023-07-19","cited_by_count":3,"area":null},{"id":"2405.15010","title":"Parameter-free Clipped Gradient Descent Meets Polyak","created":"2024-05-23","cited_by_count":3,"area":null},{"id":"2503.00229","title":"Armijo Line-search Can Make (Stochastic) Gradient Descent Provably Faster","created":"2025-02-28","cited_by_count":3,"area":null},{"id":"2507.09093","title":"Sharp High-Probability Rates for Nonlinear SGD under Heavy-Tailed Noise via Symmetrization","created":"2025-07-12","cited_by_count":3,"area":null},{"id":"2510.22421","title":"Extragradient Method for $(L_0, L_1)$-Lipschitz Root-finding Problems","created":"2025-10-25","cited_by_count":3,"area":null},{"id":"2302.02971","title":"U-Clip: On-Average Unbiased Stochastic Gradient Clipping","created":"2023-02-06","cited_by_count":2,"area":null},{"id":"2403.00853","title":"Parallel Momentum Methods Under Biased Gradient Estimations","created":"2024-02-29","cited_by_count":2,"area":null},{"id":"2509.15399","title":"Adaptive Algorithms with Sharp Convergence Rates for Stochastic Hierarchical Optimization","created":"2025-09-18","cited_by_count":2,"area":null},{"id":"2605.11838","title":"Gradient Clipping Beyond Vector Norms: A Spectral Approach for Matrix-Valued Parameters","created":"2026-05-12","cited_by_count":2,"area":null},{"id":"2605.18174","title":"Ringmaster LMO: Asynchronous Linear Minimization Oracle Momentum Method","created":"2026-05-18","cited_by_count":2,"area":null},{"id":"2606.14560","title":"Free Heavy-Tailed Lunch for Muon: A Theoretical Justification of Empirical Success","created":"2026-06-12","cited_by_count":2,"area":null},{"id":"2211.04655","title":"Perturbed Iterate SGD for Lipschitz Continuous Loss Functions with Numerical Error and Adaptive Step Sizes","created":"2022-11-09","cited_by_count":1,"area":null},{"id":"2402.01621","title":"Stochastic Two Points Method for Deep Model Zeroth-order Optimization","created":"2024-02-02","cited_by_count":1,"area":null},{"id":"2403.15244","title":"A Stochastic Quasi-Newton Method for Non-convex Optimization with Non-uniform Smoothness","created":"2024-03-22","cited_by_count":1,"area":null},{"id":"2411.03059","title":"Enhancing DP-SGD through Non-monotonous Adaptive Scaling Gradient Weight","created":"2024-11-05","cited_by_count":1,"area":null},{"id":"2503.03908","title":"On the Convergence of Adam-Type Algorithm for Bilevel Optimization under Unbounded Smoothness","created":"2025-03-05","cited_by_count":1,"area":null},{"id":"2510.23463","title":"Differential Privacy as a Perk: Federated Learning over Multiple-Access Fading Channels with a Multi-Antenna Base Station","created":"2025-10-27","cited_by_count":1,"area":null},{"id":"2602.05657","title":"Tight Long-Term Tail Decay of (Clipped) SGD in Non-Convex Optimization","created":"2026-02-05","cited_by_count":1,"area":null},{"id":"2607.04233","title":"Unified convergence analysis for gradient descent optimization methods in the training of deep neural networks","created":"2026-07-05","cited_by_count":1,"area":null},{"id":"2306.10278","title":"Adaptive Strategies in Non-convex Optimization","created":"2023-06-17","cited_by_count":0,"area":null},{"id":"2409.13672","title":"Recent Advances in Non-convex Smoothness Conditions and Applicability to Deep Linear Neural Networks","created":"2024-09-20","cited_by_count":0,"area":null},{"id":"2410.05807","title":"Extended convexity and smoothness and their applications in deep learning","created":"2024-10-08","cited_by_count":0,"area":null},{"id":"2507.08913","title":"Revisiting Convergence: Shuffling Complexity Beyond Lipschitz Smoothness","created":"2025-07-11","cited_by_count":0,"area":null},{"id":"2509.08726","title":"Decentralized Stochastic Nonconvex Optimization under the $(L_0,L_1)$-Smoothness","created":"2025-09-10","cited_by_count":0,"area":null},{"id":"2601.03566","title":"Provably Convergent Decentralized Optimization over Directed Graphs under Generalized Smoothness","created":"2026-01-07","cited_by_count":0,"area":null},{"id":"2603.12512","title":"Byzantine-Robust Optimization under $(L_0, L_1)$-Smoothness","created":"2026-03-12","cited_by_count":0,"area":null},{"id":"2605.11850","title":"Constrained Stochastic Spectral Preconditioning Converges for Nonconvex Objectives","created":"2026-05-12","cited_by_count":0,"area":null},{"id":"2606.12740","title":"Deep Unfolded Latent Optimally Partitioned-l2/l1 Networks for Data-driven Block-Sparse Recovery","created":"2026-06-10","cited_by_count":0,"area":null},{"id":"2606.13287","title":"Clipping Makes Distributed and Federated Asynchronous SGD Robust to Stragglers","created":"2026-06-11","cited_by_count":0,"area":null},{"id":"2609.29458","title":"Precise Convergence Speed of Clipped SGD","created":"2026-09-24","cited_by_count":0,"area":null},{"id":"2609.39357","title":"Robustifying Asynchronous SGD via Soft Throttling","created":"2026-09-30","cited_by_count":0,"area":null}],"next_cursor":null}