{"total":35,"rows":[{"id":"2305.17490","title":"The Implicit Regularization of Dynamical Stability in Stochastic Gradient Descent","created":"2023-05-27","cited_by_count":44,"area":null},{"id":"2102.05375","title":"Strength of Minibatch Noise in SGD","created":"2021-02-10","cited_by_count":39,"area":null},{"id":"2105.09557","title":"Power-law escape rate of SGD","created":"2021-05-20","cited_by_count":29,"area":null},{"id":"2202.04777","title":"Exact Solutions of a Deep Linear Network","created":"2022-02-10","cited_by_count":24,"area":null},{"id":"2410.10373","title":"Sharpness-Aware Minimization Efficiently Selects Flatter Minima Late in Training","created":"2024-10-14","cited_by_count":24,"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":"2402.07193","title":"Parameter Symmetry and Noise Equilibrium of Stochastic Gradient Descent","created":"2024-02-11","cited_by_count":19,"area":null},{"id":"2306.02913","title":"Decentralized SGD and Average-direction SAM are Asymptotically Equivalent","created":"2023-06-05","cited_by_count":15,"area":null},{"id":"2212.02083","title":"On the Overlooked Structure of Stochastic Gradients","created":"2022-12-05","cited_by_count":13,"area":null},{"id":"2402.05173","title":"Towards Understanding Inductive Bias in Transformers: A View From Infinity","created":"2024-02-07","cited_by_count":13,"area":null},{"id":"2211.10691","title":"Two Facets of SDE Under an Information-Theoretic Lens: Generalization of SGD via Training Trajectories and via Terminal States","created":"2022-11-19","cited_by_count":11,"area":null},{"id":"2301.12309","title":"On the Lipschitz Constant of Deep Networks and Double Descent","created":"2023-01-28","cited_by_count":11,"area":null},{"id":"2302.01952","title":"On a continuous time model of gradient descent dynamics and instability in deep learning","created":"2023-02-03","cited_by_count":11,"area":null},{"id":"2306.07850","title":"Exact Mean Square Linear Stability Analysis for SGD","created":"2023-06-13","cited_by_count":11,"area":null},{"id":"2410.03006","title":"Formation of Representations in Neural Networks","created":"2024-10-03","cited_by_count":10,"area":null},{"id":"2310.00692","title":"A Theoretical Analysis of Noise Geometry in Stochastic Gradient Descent","created":"2023-10-01","cited_by_count":9,"area":null},{"id":"2505.12387","title":"Neural Thermodynamics: Entropic Forces in Deep and Universal Representation Learning","created":"2025-05-18","cited_by_count":9,"area":null},{"id":"2107.11774","title":"SGD with a Constant Large Learning Rate Can Converge to Local Maxima","created":"2021-07-25","cited_by_count":8,"area":null},{"id":"2505.23489","title":"SGD as Free Energy Minimization: A Thermodynamic View on Neural Network Training","created":"2025-05-29","cited_by_count":4,"area":null},{"id":"2605.26895","title":"Negligible in Size, Significant in Effect: On Scale Vectors in Large Language Models","created":"2026-05-26","cited_by_count":4,"area":null},{"id":"2201.12724","title":"Stochastic Neural Networks with Infinite Width are Deterministic","created":"2022-01-30","cited_by_count":3,"area":null},{"id":"2306.02618","title":"Enhance Diffusion to Improve Robust Generalization","created":"2023-06-05","cited_by_count":3,"area":null},{"id":"2602.14789","title":"On the Stability of Nonlinear Dynamics in GD and SGD: Beyond Quadratic Potentials","created":"2026-02-16","cited_by_count":3,"area":null},{"id":"2306.05300","title":"Anti-Correlated Noise in Epoch-Based Stochastic Gradient Descent: Implications for Weight Variances in Flat Directions","created":"2023-06-08","cited_by_count":2,"area":null},{"id":"2406.13041","title":"Accelerated Stochastic Min-Max Optimization Based on Bias-corrected Momentum","created":"2024-06-18","cited_by_count":2,"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":"2512.06297","title":"Entropic Confinement and Mode Connectivity in Overparameterized Neural Networks","created":"2025-12-06","cited_by_count":1,"area":null},{"id":"2105.07222","title":"On the Distributional Properties of Adaptive Gradients","created":"2021-05-15","cited_by_count":0,"area":null},{"id":"2410.07719","title":"How Learning Dynamics Drive Adversarially Robust Generalization?","created":"2024-10-10","cited_by_count":0,"area":null},{"id":"2505.18069","title":"Ubiquity of Emergent Hebbian Dynamics in Regularized Learning","created":"2025-05-23","cited_by_count":0,"area":null},{"id":"2507.05309","title":"Neural Velocity for hyperparameter tuning","created":"2025-07-07","cited_by_count":0,"area":null},{"id":"2606.00293","title":"Accurate Large-sample Uncertainty Quantification using Stochastic Gradient Markov Chain Monte Carlo","created":"2026-05-29","cited_by_count":0,"area":null},{"id":"2609.32861","title":"Muon Under Gradient Noise and the Limits of Orthogonalization Near Optima","created":"2026-09-26","cited_by_count":0,"area":null},{"id":"2610.00615","title":"Learning the identity: a case study of how SGD selects among functional decompositions","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2610.15126","title":"Data-Topology Compatibility Enables Personalization in Decentralized Learning","created":"2026-10-10","cited_by_count":0,"area":null}],"next_cursor":null}