{"total":171,"rows":[{"id":"2402.16788","title":"Why Transformers Need Adam: A Hessian Perspective","created":"2024-02-26","cited_by_count":124,"area":null},{"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":"2402.01868","title":"Challenges in Training PINNs: A Loss Landscape Perspective","created":"2024-02-02","cited_by_count":113,"area":null},{"id":"2207.14484","title":"Adaptive Gradient Methods at the Edge of Stability","created":"2022-07-29","cited_by_count":101,"area":null},{"id":"2304.13972","title":"Convergence of Adam Under Relaxed Assumptions","created":"2023-04-27","cited_by_count":99,"area":null},{"id":"2506.15054","title":"Muon Optimizes Under Spectral Norm Constraints","created":"2025-06-18","cited_by_count":86,"area":null},{"id":"2208.11195","title":"Robustness to Unbounded Smoothness of Generalized SignSGD","created":"2022-08-23","cited_by_count":81,"area":null},{"id":"2404.04454","title":"Implicit Bias of AdamW: $\\ell_\\infty$ Norm Constrained Optimization","created":"2024-04-05","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":"2306.00204","title":"Toward Understanding Why Adam Converges Faster Than SGD for Transformers","created":"2023-05-31","cited_by_count":53,"area":null},{"id":"2112.03459","title":"A Novel Convergence Analysis for Algorithms of the Adam Family","created":"2021-12-07","cited_by_count":50,"area":null},{"id":"2108.11371","title":"Understanding the Generalization of Adam in Learning Neural Networks with Proper Regularization","created":"2021-08-25","cited_by_count":49,"area":null},{"id":"2302.14843","title":"High Probability Convergence of Stochastic Gradient Methods","created":"2023-02-28","cited_by_count":49,"area":null},{"id":"2509.26030","title":"Muon Outperforms Adam in Tail-End Associative Memory Learning","created":"2025-09-30","cited_by_count":46,"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":"2105.01650","title":"Stochastic gradient descent with noise of machine learning type. Part I: Discrete time analysis","created":"2021-05-04","cited_by_count":39,"area":null},{"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,"area":null},{"id":"2410.16103","title":"LDAdam: Adaptive Optimization from Low-Dimensional Gradient Statistics","created":"2024-10-21","cited_by_count":38,"area":null},{"id":"2101.11075","title":"Adaptivity without Compromise: A Momentumized, Adaptive, Dual Averaged Gradient Method for Stochastic Optimization","created":"2021-01-26","cited_by_count":28,"area":null},{"id":"2404.02827","title":"BAdam: A Memory Efficient Full Parameter Optimization Method for Large Language Models","created":"2024-04-03","cited_by_count":27,"area":null},{"id":"2402.01567","title":"Understanding Adam Optimizer via Online Learning of Updates: Adam is FTRL in Disguise","created":"2024-02-02","cited_by_count":26,"area":null},{"id":"2101.05471","title":"Towards Practical Adam: Non-Convexity, Convergence Theory, and Mini-Batch Acceleration","created":"2021-01-14","cited_by_count":25,"area":null},{"id":"2211.02254","title":"How Does Adaptive Optimization Impact Local Neural Network Geometry?","created":"2022-11-04","cited_by_count":24,"area":null},{"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,"area":null},{"id":"2405.18199","title":"Adam with model exponential moving average is effective for nonconvex optimization","created":"2024-05-28","cited_by_count":23,"area":null},{"id":"2410.08198","title":"Adam Exploits $\\ell_\\infty$-geometry of Loss Landscape via Coordinate-wise Adaptivity","created":"2024-10-10","cited_by_count":23,"area":null},{"id":"2509.02981","title":"AdaGrad Meets Muon: Adaptive Stepsizes for Orthogonal Updates","created":"2025-09-03","cited_by_count":23,"area":null},{"id":"2110.03891","title":"Does Momentum Change the Implicit Regularization on Separable Data?","created":"2021-10-08","cited_by_count":22,"area":null},{"id":"2302.04552","title":"Optimistic Online Mirror Descent for Bridging Stochastic and Adversarial Online Convex Optimization","created":"2023-02-09","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":"2402.03982","title":"On Convergence of Adam for Stochastic Optimization under Relaxed Assumptions","created":"2024-02-06","cited_by_count":21,"area":null},{"id":"2402.07114","title":"Towards Quantifying the Preconditioning Effect of Adam","created":"2024-02-11","cited_by_count":19,"area":null},{"id":"2405.15593","title":"MicroAdam: Accurate Adaptive Optimization with Low Space Overhead and Provable Convergence","created":"2024-05-24","cited_by_count":19,"area":null},{"id":"2405.18187","title":"AlignIQL: Policy Alignment in Implicit Q-Learning through Constrained Optimization","created":"2024-05-28","cited_by_count":19,"area":"offlinerl"},{"id":"2405.12807","title":"FAdam: Adam is a natural gradient optimizer using diagonal empirical Fisher information","created":"2024-05-21","cited_by_count":18,"area":null},{"id":"2411.02853","title":"ADOPT: Modified Adam Can Converge with Any $\\beta_2$ with the Optimal Rate","created":"2024-11-05","cited_by_count":18,"area":null},{"id":"2406.04592","title":"Provable Complexity Improvement of AdaGrad over SGD: Upper and Lower Bounds in Stochastic Non-Convex Optimization","created":"2024-06-07","cited_by_count":16,"area":null},{"id":"2202.06009","title":"Maximizing Communication Efficiency for Large-scale Training via 0/1 Adam","created":"2022-02-12","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":"2407.08100","title":"Non-convergence of Adam and other adaptive stochastic gradient descent optimization methods for non-vanishing learning rates","created":"2024-07-11","cited_by_count":15,"area":null},{"id":"2407.21078","title":"Convergence rates for the Adam optimizer","created":"2024-07-29","cited_by_count":15,"area":null},{"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,"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":"2104.14840","title":"Unified Convergence Analysis for Adaptive Optimization with Moving Average Estimator","created":"2021-04-30","cited_by_count":13,"area":null},{"id":"2206.07553","title":"On the fast convergence of minibatch heavy ball momentum","created":"2022-06-15","cited_by_count":13,"area":null},{"id":"2406.04142","title":"Stochastic Polyak Step-sizes and Momentum: Convergence Guarantees and Practical Performance","created":"2024-06-06","cited_by_count":13,"area":null},{"id":"2506.04805","title":"Adaptive Preconditioners Trigger Loss Spikes in Adam","created":"2025-06-05","cited_by_count":13,"area":null},{"id":"2510.12402","title":"Cautious Weight Decay","created":"2025-10-14","cited_by_count":13,"area":null},{"id":"2506.01260","title":"Subspace Networks: Scaling Decentralized Training with Communication-Efficient Model Parallelism","created":"2025-06-02","cited_by_count":12,"area":null},{"id":"2506.23803","title":"SGD with Adaptive Preconditioning: Unified Analysis and Momentum Acceleration","created":"2025-06-30","cited_by_count":12,"area":null},{"id":"2209.06302","title":"Optimization without Backpropagation","created":"2022-09-13","cited_by_count":11,"area":null},{"id":"2410.19964","title":"Understanding Adam Requires Better Rotation Dependent Assumptions","created":"2024-10-25","cited_by_count":11,"area":null},{"id":"2411.19870","title":"DeMo: Decoupled Momentum Optimization","created":"2024-11-29","cited_by_count":11,"area":null},{"id":"2602.16340","title":"The Implicit Bias of Adam and Muon on Smooth Homogeneous Neural Networks","created":"2026-02-18","cited_by_count":11,"area":null},{"id":"2502.20566","title":"Stochastic Rounding for LLM Training: Theory and Practice","created":"2025-02-27","cited_by_count":10,"area":null},{"id":"2306.02527","title":"Searching for Optimal Per-Coordinate Step-sizes with Multidimensional Backtracking","created":"2023-06-05","cited_by_count":9,"area":null},{"id":"2402.05155","title":"Non-convergence to global minimizers for Adam and stochastic gradient descent optimization and constructions of local minimizers in the training of artificial neural networks","created":"2024-02-07","cited_by_count":9,"area":null},{"id":"2210.17478","title":"TiAda: A Time-scale Adaptive Algorithm for Nonconvex Minimax Optimization","created":"2022-10-31","cited_by_count":8,"area":null},{"id":"2311.02000","title":"High Probability Convergence of Adam Under Unbounded Gradients and Affine Variance Noise","created":"2023-11-03","cited_by_count":8,"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":"2403.02648","title":"Remove that Square Root: A New Efficient Scale-Invariant Version of AdaGrad","created":"2024-03-05","cited_by_count":8,"area":null},{"id":"2407.20454","title":"CoMMIT: Coordinated Multimodal Instruction Tuning","created":"2024-07-29","cited_by_count":8,"area":"mllm"},{"id":"2504.19426","title":"Sharp higher order convergence rates for the Adam optimizer","created":"2025-04-28","cited_by_count":8,"area":null},{"id":"2505.11840","title":"On the $O(\\frac{\\sqrt{d}}{K^{1/4}})$ Convergence Rate of AdamW Measured by $\\ell_1$ Norm","created":"2025-05-17","cited_by_count":8,"area":null},{"id":"2505.24275","title":"GradPower: Powering Gradients for Faster Language Model Pre-Training","created":"2025-05-30","cited_by_count":8,"area":null},{"id":"2201.11204","title":"On the Convergence of mSGD and AdaGrad for Stochastic Optimization","created":"2022-01-26","cited_by_count":7,"area":null},{"id":"2303.01370","title":"Non asymptotic analysis of Adaptive stochastic gradient algorithms and applications","created":"2023-03-01","cited_by_count":7,"area":null},{"id":"2110.04844","title":"Frequency-aware SGD for Efficient Embedding Learning with Provable Benefits","created":"2021-10-10","cited_by_count":6,"area":null},{"id":"2401.08893","title":"MADA: Meta-Adaptive Optimizers through hyper-gradient Descent","created":"2024-01-17","cited_by_count":6,"area":null},{"id":"2402.05453","title":"Mitigating Privacy Risk in Membership Inference by Convex-Concave Loss","created":"2024-02-08","cited_by_count":6,"area":"safety"},{"id":"2406.11257","title":"ExCP: Extreme LLM Checkpoint Compression via Weight-Momentum Joint Shrinking","created":"2024-06-17","cited_by_count":6,"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":"2606.04662","title":"Why Muon Outperforms Adam: A Curvature Perspective","created":"2026-06-03","cited_by_count":6,"area":null},{"id":"2206.00285","title":"Stochastic Gradient Methods with Preconditioned Updates","created":"2022-06-01","cited_by_count":5,"area":null},{"id":"2310.08858","title":"Adam-family Methods with Decoupled Weight Decay in Deep Learning","created":"2023-10-13","cited_by_count":5,"area":null},{"id":"2402.02857","title":"Non-asymptotic Analysis of Biased Adaptive Stochastic Approximation","created":"2024-02-05","cited_by_count":5,"area":null},{"id":"2502.17340","title":"Low-rank bias, weight decay, and model merging in neural networks","created":"2025-02-24","cited_by_count":5,"area":null},{"id":"2506.01863","title":"Unified Scaling Laws for Compressed Representations","created":"2025-06-02","cited_by_count":5,"area":null},{"id":"2108.09134","title":"Accelerating Federated Learning with a Global Biased Optimiser","created":"2021-08-20","cited_by_count":4,"area":null},{"id":"2109.14375","title":"Dynamic Regret Analysis for Online Meta-Learning","created":"2021-09-29","cited_by_count":4,"area":null},{"id":"2210.11078","title":"Large-batch Optimization for Dense Visual Predictions","created":"2022-10-20","cited_by_count":4,"area":null},{"id":"2210.11113","title":"PAC-Bayesian Learning of Optimization Algorithms","created":"2022-10-20","cited_by_count":4,"area":null},{"id":"2403.06528","title":"Adaptive Federated Learning Over the Air","created":"2024-03-11","cited_by_count":4,"area":null},{"id":"2410.11998","title":"From promise to practice: realizing high-performance decentralized training","created":"2024-10-15","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":"2602.08372","title":"Dynamic Regret via Discounted-to-Dynamic Reduction with Applications to Curved Losses and Adam Optimizer","created":"2026-02-09","cited_by_count":4,"area":null},{"id":"2603.09581","title":"Towards Understanding Adam Convergence on Highly Degenerate Polynomials","created":"2026-03-10","cited_by_count":4,"area":null},{"id":"2206.08303","title":"On Scaled Methods for Saddle Point Problems","created":"2022-06-16","cited_by_count":3,"area":null},{"id":"2407.03593","title":"Green Multigrid Network","created":"2024-07-04","cited_by_count":3,"area":null},{"id":"2411.04775","title":"Learning dynamical systems from data: Gradient-based dictionary optimization","created":"2024-11-07","cited_by_count":3,"area":null},{"id":"2504.04274","title":"Randomised Splitting Methods and Stochastic Gradient Descent","created":"2025-04-05","cited_by_count":3,"area":null},{"id":"2504.18911","title":"A Langevin sampling algorithm inspired by the Adam optimizer","created":"2025-04-26","cited_by_count":3,"area":null},{"id":"2505.24399","title":"LightSAM: Parameter-Agnostic Sharpness-Aware Minimization","created":"2025-05-30","cited_by_count":3,"area":null},{"id":"2507.08963","title":"Stochastic Approximation with Block Coordinate Optimal Stepsizes","created":"2025-07-11","cited_by_count":3,"area":null},{"id":"2511.07843","title":"DP-AdamW: Investigating Decoupled Weight Decay and Bias Correction in Private Deep Learning","created":"2025-11-11","cited_by_count":3,"area":null},{"id":"2603.18899","title":"Uniform a priori bounds and error analysis for the Adam stochastic gradient descent optimization method","created":"2026-03-19","cited_by_count":3,"area":null},{"id":"2605.18694","title":"Can Adaptive Gradient Methods Converge under Heavy-Tailed Noise? A Case Study of AdaGrad","created":"2026-05-18","cited_by_count":3,"area":null},{"id":"2606.09658","title":"Muon Learns More Robust and Transferable Features than Adam","created":"2026-06-08","cited_by_count":3,"area":null},{"id":"2106.00092","title":"Generalized AdaGrad (G-AdaGrad) and Adam: A State-Space Perspective","created":"2021-05-31","cited_by_count":2,"area":null}],"next_cursor":"100"}