{"total":35,"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":"2102.02888","title":"1-bit Adam: Communication Efficient Large-Scale Training with Adam's Convergence Speed","created":"2021-02-04","cited_by_count":75,"area":null},{"id":"2204.02833","title":"High Probability Bounds for a Class of Nonconvex Algorithms with AdaGrad Stepsize","created":"2022-04-06","cited_by_count":40,"area":null},{"id":"2505.21829","title":"In Search of Adam's Secret Sauce","created":"2025-05-27","cited_by_count":40,"area":null},{"id":"2302.08783","title":"SGD with AdaGrad Stepsizes: Full Adaptivity with High Probability to Unknown Parameters, Unbounded Gradients and Affine Variance","created":"2023-02-17","cited_by_count":30,"area":null},{"id":"2501.06842","title":"SPAM: Spike-Aware Adam with Momentum Reset for Stable LLM Training","created":"2025-01-12","cited_by_count":28,"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":"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":"2212.00309","title":"Differentially Private Adaptive Optimization with Delayed Preconditioners","created":"2022-12-01","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":"2111.00705","title":"Communication-Compressed Adaptive Gradient Method for Distributed Nonconvex Optimization","created":"2021-11-01","cited_by_count":12,"area":null},{"id":"2402.03126","title":"How Free is Parameter-Free Stochastic Optimization?","created":"2024-02-05","cited_by_count":12,"area":null},{"id":"2201.06714","title":"AdaTerm: Adaptive T-Distribution Estimated Robust Moments for Noise-Robust Stochastic Gradient Optimization","created":"2022-01-18","cited_by_count":11,"area":null},{"id":"2102.07002","title":"On the Last Iterate Convergence of Momentum Methods","created":"2021-02-13","cited_by_count":10,"area":null},{"id":"2210.05607","title":"Divergence Results and Convergence of a Variance Reduced Version of ADAM","created":"2022-10-11","cited_by_count":8,"area":null},{"id":"2102.07314","title":"The Role of Momentum Parameters in the Optimal Convergence of Adaptive Polyak's Heavy-ball Methods","created":"2021-02-15","cited_by_count":7,"area":null},{"id":"2307.00631","title":"Bidirectional Looking with A Novel Double Exponential Moving Average to Adaptive and Non-adaptive Momentum Optimizers","created":"2023-07-02","cited_by_count":6,"area":null},{"id":"2604.15416","title":"StoSignSGD: Unbiased Structural Stochasticity Fixes SignSGD for Training Large Language Models","created":"2026-04-16","cited_by_count":5,"area":null},{"id":"2110.05454","title":"Momentum Centering and Asynchronous Update for Adaptive Gradient Methods","created":"2021-10-11","cited_by_count":4,"area":null},{"id":"2209.01608","title":"Dynamic Regret of Adaptive Gradient Methods for Strongly Convex Problems","created":"2022-09-04","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":"2202.06152","title":"Analysis of Dual-Based PID Controllers through Convolutional Mirror Descent","created":"2022-02-12","cited_by_count":3,"area":null},{"id":"2208.04065","title":"Optimistic Optimisation of Composite Objective with Exponentiated Update","created":"2022-08-08","cited_by_count":3,"area":null},{"id":"2510.04407","title":"Scale-Invariant Regret Matching and Online Learning with Optimal Convergence: Bridging Theory and Practice in Zero-Sum Games","created":"2025-10-06","cited_by_count":3,"area":null},{"id":"2411.19647","title":"CAdam: Confidence-Based Optimization for Online Learning","created":"2024-11-29","cited_by_count":2,"area":null},{"id":"2412.19444","title":"Towards Simple and Provable Parameter-Free Adaptive Gradient Methods","created":"2024-12-27","cited_by_count":2,"area":null},{"id":"2510.03478","title":"How to Set $\\beta_1, \\beta_2$ in Adam: An Online Learning Perspective","created":"2025-10-03","cited_by_count":2,"area":null},{"id":"2210.07454","title":"Communication-Efficient Adam-Type Algorithms for Distributed Data Mining","created":"2022-10-14","cited_by_count":1,"area":null},{"id":"2512.06795","title":"ADAM Optimization with Adaptive Batch Selection","created":"2025-12-07","cited_by_count":1,"area":null},{"id":"2606.28879","title":"Analysis of Adam Algorithms for Stochastic Dynamic Systems","created":"2026-06-27","cited_by_count":1,"area":null},{"id":"2607.03519","title":"On the Convergence of Adam, Revisited","created":"2026-07-03","cited_by_count":1,"area":null},{"id":"2107.01525","title":"AdaL: Adaptive Gradient Transformation Contributes to Convergences and Generalizations","created":"2021-07-04","cited_by_count":0,"area":null},{"id":"2107.08377","title":"A New Adaptive Gradient Method with Gradient Decomposition","created":"2021-07-18","cited_by_count":0,"area":null},{"id":"2503.09411","title":"Learning Rate Annealing Improves Tuning Robustness in Stochastic Optimization","created":"2025-03-12","cited_by_count":0,"area":null}],"next_cursor":null}