{"total":57,"rows":[{"id":"2106.09524","title":"Implicit Bias of SGD for Diagonal Linear Networks: a Provable Benefit of Stochasticity","created":"2021-06-17","cited_by_count":110,"area":null},{"id":"2102.09972","title":"Implicit Regularization in Tensor Factorization","created":"2021-02-19","cited_by_count":44,"area":null},{"id":"2102.04877","title":"Noisy Recurrent Neural Networks","created":"2021-02-09","cited_by_count":42,"area":null},{"id":"2306.04251","title":"Stochastic Collapse: How Gradient Noise Attracts SGD Dynamics Towards Simpler Subnetworks","created":"2023-06-07","cited_by_count":39,"area":null},{"id":"2406.10650","title":"The Implicit Bias of Adam on Separable Data","created":"2024-06-15","cited_by_count":36,"area":null},{"id":"2108.04552","title":"The Benefits of Implicit Regularization from SGD in Least Squares Problems","created":"2021-08-10","cited_by_count":32,"area":null},{"id":"2212.14032","title":"On Implicit Bias in Overparameterized Bilevel Optimization","created":"2022-12-28","cited_by_count":30,"area":null},{"id":"2206.09841","title":"Label noise (stochastic) gradient descent implicitly solves the Lasso for quadratic parametrisation","created":"2022-06-20","cited_by_count":29,"area":null},{"id":"2112.03215","title":"Multi-scale Feature Learning Dynamics: Insights for Double Descent","created":"2021-12-06","cited_by_count":24,"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":"2105.00303","title":"RATT: Leveraging Unlabeled Data to Guarantee Generalization","created":"2021-05-01","cited_by_count":20,"area":null},{"id":"2107.09133","title":"The Limiting Dynamics of SGD: Modified Loss, Phase Space Oscillations, and Anomalous Diffusion","created":"2021-07-19","cited_by_count":19,"area":null},{"id":"2202.01263","title":"NoisyMix: Boosting Model Robustness to Common Corruptions","created":"2022-02-02","cited_by_count":17,"area":null},{"id":"2108.02883","title":"Interpolation can hurt robust generalization even when there is no noise","created":"2021-08-05","cited_by_count":15,"area":null},{"id":"2210.15898","title":"Toward Equation of Motion for Deep Neural Networks: Continuous-time Gradient Descent and Discretization Error Analysis","created":"2022-10-28","cited_by_count":13,"area":null},{"id":"2206.01274","title":"Algorithmic Stability of Heavy-Tailed Stochastic Gradient Descent on Least Squares","created":"2022-06-02","cited_by_count":12,"area":null},{"id":"2203.11864","title":"On the (Non-)Robustness of Two-Layer Neural Networks in Different Learning Regimes","created":"2022-03-22","cited_by_count":11,"area":null},{"id":"2205.07331","title":"Sobolev Acceleration and Statistical Optimality for Learning Elliptic Equations via Gradient Descent","created":"2022-05-15","cited_by_count":11,"area":null},{"id":"2406.04425","title":"On Regularization via Early Stopping for Least Squares Regression","created":"2024-06-06","cited_by_count":11,"area":null},{"id":"2305.18496","title":"Generalized equivalences between subsampling and ridge regularization","created":"2023-05-29","cited_by_count":10,"area":null},{"id":"2306.08590","title":"Beyond Implicit Bias: The Insignificance of SGD Noise in Online Learning","created":"2023-06-14","cited_by_count":10,"area":null},{"id":"2112.03754","title":"A Continuous-time Stochastic Gradient Descent Method for Continuous Data","created":"2021-12-07","cited_by_count":7,"area":null},{"id":"2104.08928","title":"Group-Sparse Matrix Factorization for Transfer Learning of Word Embeddings","created":"2021-04-18","cited_by_count":6,"area":null},{"id":"2108.11872","title":"Comparing Classes of Estimators: When does Gradient Descent Beat Ridge Regression in Linear Models?","created":"2021-08-26","cited_by_count":5,"area":null},{"id":"2109.10935","title":"Robust Generalization of Quadratic Neural Networks via Function Identification","created":"2021-09-22","cited_by_count":5,"area":null},{"id":"2206.08558","title":"How You Start Matters for Generalization","created":"2022-06-17","cited_by_count":5,"area":null},{"id":"2202.09885","title":"On Optimal Early Stopping: Over-informative versus Under-informative Parametrization","created":"2022-02-20","cited_by_count":4,"area":null},{"id":"2301.13486","title":"Robust Linear Regression: Gradient-descent, Early-stopping, and Beyond","created":"2023-01-31","cited_by_count":4,"area":null},{"id":"2402.16793","title":"Failures and Successes of Cross-Validation for Early-Stopped Gradient Descent","created":"2024-02-26","cited_by_count":4,"area":null},{"id":"2303.17805","title":"On the Effect of Initialization: The Scaling Path of 2-Layer Neural Networks","created":"2023-03-31","cited_by_count":3,"area":null},{"id":"2403.08585","title":"Improving Implicit Regularization of SGD with Preconditioning for Least Square Problems","created":"2024-03-13","cited_by_count":3,"area":null},{"id":"2407.02322","title":"Stochastic Differential Equations models for Least-Squares Stochastic Gradient Descent","created":"2024-07-02","cited_by_count":3,"area":null},{"id":"2204.04476","title":"High-dimensional Asymptotics of Langevin Dynamics in Spiked Matrix Models","created":"2022-04-09","cited_by_count":2,"area":null},{"id":"2402.08344","title":"Implicit Bias in Noisy-SGD: With Applications to Differentially Private Training","created":"2024-02-13","cited_by_count":2,"area":null},{"id":"2503.05542","title":"Comparing regularisation paths of (conjugate) gradient estimators in ridge regression","created":"2025-03-07","cited_by_count":2,"area":null},{"id":"2512.24999","title":"Basic Inequalities for First-Order Optimization with Applications to Statistical Risk Analysis","created":"2025-12-31","cited_by_count":2,"area":null},{"id":"2205.00058","title":"Implicit Regularization Properties of Variance Reduced Stochastic Mirror Descent","created":"2022-04-29","cited_by_count":1,"area":null},{"id":"2205.00061","title":"The Directional Bias Helps Stochastic Gradient Descent to Generalize in Kernel Regression Models","created":"2022-04-29","cited_by_count":1,"area":null},{"id":"2302.09727","title":"Statistical Inference for Linear Functionals of Online SGD in High-dimensional Linear Regression","created":"2023-02-20","cited_by_count":1,"area":null},{"id":"2307.02454","title":"Transgressing the boundaries: towards a rigorous understanding of deep learning and its (non-)robustness","created":"2023-07-05","cited_by_count":1,"area":null},{"id":"2311.14120","title":"Weight fluctuations in (deep) linear neural networks and a derivation of the inverse-variance flatness relation","created":"2023-11-23","cited_by_count":1,"area":null},{"id":"2402.07626","title":"Stochastic Gradient Flow Dynamics of Test Risk and its Exact Solution for Weak Features","created":"2024-02-12","cited_by_count":1,"area":null},{"id":"2408.15784","title":"Implicit Regularization Paths of Weighted Neural Representations","created":"2024-08-28","cited_by_count":1,"area":null},{"id":"2510.19734","title":"Statistical Inference for Linear Functionals of Online Least-squares SGD when $t \\gtrsim d^{1+\\delta}$","created":"2025-10-22","cited_by_count":1,"area":null},{"id":"2602.12257","title":"On the implicit regularization of Langevin dynamics with projected noise","created":"2026-02-12","cited_by_count":1,"area":null},{"id":"2107.02253","title":"Generalization by design: Shortcuts to Generalization in Deep Learning","created":"2021-07-05","cited_by_count":0,"area":null},{"id":"2110.03273","title":"AgFlow: Fast Model Selection of Penalized PCA via Implicit Regularization Effects of Gradient Flow","created":"2021-10-07","cited_by_count":0,"area":null},{"id":"2201.05405","title":"The Implicit Regularization of Momentum Gradient Descent with Early Stopping","created":"2022-01-14","cited_by_count":0,"area":null},{"id":"2201.08311","title":"Accelerated Gradient Flow: Risk, Stability, and Implicit Regularization","created":"2022-01-20","cited_by_count":0,"area":null},{"id":"2202.11883","title":"A Note on Machine Learning Approach for Computational Imaging","created":"2022-02-24","cited_by_count":0,"area":null},{"id":"2304.00320","title":"Doubly Stochastic Models: Learning with Unbiased Label Noises and Inference Stability","created":"2023-04-01","cited_by_count":0,"area":null},{"id":"2406.03696","title":"Error dynamics of mini-batch gradient descent with random reshuffling for least squares regression","created":"2024-06-06","cited_by_count":0,"area":null},{"id":"2507.03843","title":"A Log-Linear Analytics Approach to Cost Model Regularization for Inpatient Stays through Diagnostic Code Merging","created":"2025-07-05","cited_by_count":0,"area":null},{"id":"2605.30059","title":"Ridge Regression from Poisson Resetting: A Renewal Perspective on Spectral Regularization","created":"2026-05-28","cited_by_count":0,"area":null},{"id":"2607.22474","title":"Beyond Negative-Ridge Endpoints: Mixed-Sign Spectral Regularization via Negative-Shifted Gradient Descent","created":"2026-07-24","cited_by_count":0,"area":null},{"id":"2609.08219","title":"Speed Limit for Information Acquisition in Stochastic Learning Dynamics","created":"2026-09-08","cited_by_count":0,"area":null},{"id":"2610.16845","title":"Feature Normalization under Finite Training Budgets","created":"2026-10-12","cited_by_count":0,"area":null}],"next_cursor":null}