{"total":24,"rows":[{"id":"2310.07831","title":"Optimal Linear Decay Learning Rate Schedules and Further Refinements","created":"2023-10-11","cited_by_count":43,"area":null},{"id":"2305.16284","title":"DoWG Unleashed: An Efficient Universal Parameter-Free Gradient Descent Method","created":"2023-05-25","cited_by_count":35,"area":null},{"id":"2406.15244","title":"AdaGrad under Anisotropic Smoothness","created":"2024-06-21","cited_by_count":22,"area":null},{"id":"2305.05448","title":"Robust Implicit Regularization via Weight Normalization","created":"2023-05-09","cited_by_count":12,"area":null},{"id":"2203.01400","title":"Adaptive Gradient Methods with Local Guarantees","created":"2022-03-02","cited_by_count":8,"area":null},{"id":"2306.11680","title":"The Implicit Bias of Batch Normalization in Linear Models and Two-layer Linear Convolutional Neural Networks","created":"2023-06-20","cited_by_count":8,"area":null},{"id":"2107.03331","title":"KOALA: A Kalman Optimization Algorithm with Loss Adaptivity","created":"2021-07-07","cited_by_count":6,"area":null},{"id":"2401.17401","title":"Step-size Optimization for Continual Learning","created":"2024-01-30","cited_by_count":6,"area":null},{"id":"2101.02916","title":"Accelerating Training of Batch Normalization: A Manifold Perspective","created":"2021-01-08","cited_by_count":4,"area":null},{"id":"2109.08282","title":"AdaLoss: A computationally-efficient and provably convergent adaptive gradient method","created":"2021-09-17","cited_by_count":4,"area":null},{"id":"2306.00700","title":"On the Weight Dynamics of Deep Normalized Networks","created":"2023-06-01","cited_by_count":4,"area":null},{"id":"2201.12678","title":"A Stochastic Bundle Method for Interpolating Networks","created":"2022-01-29","cited_by_count":3,"area":null},{"id":"2405.19585","title":"The High Line: Exact Risk and Learning Rate Curves of Stochastic Adaptive Learning Rate Algorithms","created":"2024-05-30","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},{"id":"2111.15317","title":"AutoDrop: Training Deep Learning Models with Automatic Learning Rate Drop","created":"2021-11-30","cited_by_count":2,"area":null},{"id":"2604.17423","title":"A unified convergence theory for adaptive first-order methods in the nonconvex case, including AdaNorm, full and diagonal AdaGrad and Muon","created":"2026-04-19","cited_by_count":2,"area":null},{"id":"2405.11389","title":"Adjacent Leader Decentralized Stochastic Gradient Descent","created":"2024-05-18","cited_by_count":1,"area":null},{"id":"2104.05447","title":"Meta-Regularization: An Approach to Adaptive Choice of the Learning Rate in Gradient Descent","created":"2021-04-12","cited_by_count":0,"area":null},{"id":"2208.00502","title":"Formal guarantees for heuristic optimization algorithms used in machine learning","created":"2022-07-31","cited_by_count":0,"area":null},{"id":"2310.13854","title":"Exponential weight averaging as damped harmonic motion","created":"2023-10-20","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":"2503.02147","title":"Frankenstein Optimizer: Harnessing the Potential by Revisiting Optimization Tricks","created":"2025-03-04","cited_by_count":0,"area":null},{"id":"2503.23016","title":"Towards Understanding the Optimization Mechanisms in Deep Learning","created":"2025-03-29","cited_by_count":0,"area":null},{"id":"2509.23052","title":"Optimization as a Dynamical System: Generative Schedules from Latent ODEs","created":"2025-09-27","cited_by_count":0,"area":null}],"next_cursor":null}