{"total":22,"rows":[{"id":"2106.06530","title":"Label Noise SGD Provably Prefers Flat Global Minimizers","created":"2021-06-11","cited_by_count":121,"area":null},{"id":"2201.02115","title":"The dynamics of representation learning in shallow, non-linear autoencoders","created":"2022-01-06","cited_by_count":27,"area":null},{"id":"2309.16314","title":"A Primer on Bayesian Neural Networks: Review and Debates","created":"2023-09-28","cited_by_count":27,"area":null},{"id":"2207.05952","title":"Implicit regularization of dropout","created":"2022-07-13","cited_by_count":25,"area":null},{"id":"2210.05021","title":"The good, the bad and the ugly sides of data augmentation: An implicit spectral regularization perspective","created":"2022-10-10","cited_by_count":24,"area":null},{"id":"2306.13853","title":"A Unified Approach to Controlling Implicit Regularization via Mirror Descent","created":"2023-06-24","cited_by_count":14,"area":null},{"id":"2503.19859","title":"An Overview of Low-Rank Structures in the Training and Adaptation of Large Models","created":"2025-03-25","cited_by_count":9,"area":null},{"id":"2102.07927","title":"Structured Dropout Variational Inference for Bayesian Neural Networks","created":"2021-02-16","cited_by_count":7,"area":null},{"id":"2404.12293","title":"Singular-limit analysis of gradient descent with noise injection","created":"2024-04-18","cited_by_count":7,"area":null},{"id":"2602.15322","title":"On Surprising Effectiveness of Masking Updates in Adaptive Optimizers","created":"2026-02-17","cited_by_count":7,"area":null},{"id":"2201.09209","title":"Weight Expansion: A New Perspective on Dropout and Generalization","created":"2022-01-23","cited_by_count":6,"area":null},{"id":"2105.11675","title":"An Upper Limit of Decaying Rate with Respect to Frequency in Deep Neural Network","created":"2021-05-25","cited_by_count":4,"area":null},{"id":"2505.07792","title":"Analytic theory of dropout regularization","created":"2025-05-12","cited_by_count":2,"area":null},{"id":"2512.13853","title":"Dropout Neural Network Training Viewed from a Percolation Perspective","created":"2025-12-15","cited_by_count":2,"area":null},{"id":"2509.24962","title":"Overlap-Adaptive Regularization for Conditional Average Treatment Effect Estimation","created":"2025-09-29","cited_by_count":1,"area":null},{"id":"2605.05436","title":"Estimating Implicit Regularization in Deep Learning","created":"2026-05-06","cited_by_count":1,"area":null},{"id":"2101.01178","title":"Advances in Electron Microscopy with Deep Learning","created":"2021-01-04","cited_by_count":0,"area":null},{"id":"2107.13270","title":"A Reflection on Learning from Data: Epistemology Issues and Limitations","created":"2021-07-28","cited_by_count":0,"area":null},{"id":"2202.03535","title":"Noise Regularizes Over-parameterized Rank One Matrix Recovery, Provably","created":"2022-02-07","cited_by_count":0,"area":null},{"id":"2305.18684","title":"ShuffleMix: Improving Representations via Channel-Wise Shuffle of Interpolated Hidden States","created":"2023-05-30","cited_by_count":0,"area":null},{"id":"2607.16761","title":"Dropout and Random Gradient Masking Are Asymptotically Equivalent in Large ResNets","created":"2026-07-18","cited_by_count":0,"area":null},{"id":"2609.32060","title":"Depth Laws for the Precision Floor of Trained Neural Networks: Amplification, Residual Scaling, and a Quantization-Aware Training Paradox","created":"2026-09-25","cited_by_count":0,"area":null}],"next_cursor":null}