{"total":14,"rows":[{"id":"2110.03677","title":"Large Learning Rate Tames Homogeneity: Convergence and Balancing Effect","created":"2021-10-07","cited_by_count":50,"area":null},{"id":"2106.14289","title":"Global Convergence of Gradient Descent for Asymmetric Low-Rank Matrix Factorization","created":"2021-06-27","cited_by_count":45,"area":null},{"id":"2210.06441","title":"How Much Data Are Augmentations Worth? An Investigation into Scaling Laws, Invariance, and Implicit Regularization","created":"2022-10-12","cited_by_count":40,"area":null},{"id":"2203.03756","title":"Flat minima generalize for low-rank matrix recovery","created":"2022-03-07","cited_by_count":28,"area":null},{"id":"2206.04613","title":"Explicit Regularization in Overparametrized Models via Noise Injection","created":"2022-06-09","cited_by_count":26,"area":null},{"id":"2212.03050","title":"Uniform-in-time propagation of chaos for mean field Langevin dynamics","created":"2022-12-06","cited_by_count":23,"area":null},{"id":"2410.06441","title":"Addax: Utilizing Zeroth-Order Gradients to Improve Memory Efficiency and Performance of SGD for Fine-Tuning Language Models","created":"2024-10-09","cited_by_count":11,"area":null},{"id":"2109.06610","title":"Statistical limits of dictionary learning: random matrix theory and the spectral replica method","created":"2021-09-14","cited_by_count":10,"area":null},{"id":"2502.07584","title":"Generalization Bounds for Markov Algorithms through Entropy Flow Computations","created":"2025-02-11","cited_by_count":2,"area":null},{"id":"2509.25783","title":"Sharpness of Minima in Deep Matrix Factorization","created":"2025-09-30","cited_by_count":2,"area":null},{"id":"2410.05022","title":"On subdifferential chain rule of matrix factorization and beyond","created":"2024-10-07","cited_by_count":0,"area":null},{"id":"2410.14667","title":"SGD Jittering: A Training Strategy for Robust and Accurate Model-Based Architectures","created":"2024-10-18","cited_by_count":0,"area":null},{"id":"2508.10435","title":"Unpacking the Implicit Norm Dynamics of Sharpness-Aware Minimization in Tensorized Models","created":"2025-08-14","cited_by_count":0,"area":null},{"id":"2511.01234","title":"A Saddle Point Remedy: Power of Variable Elimination in Non-convex Optimization","created":"2025-11-03","cited_by_count":0,"area":null}],"next_cursor":null}