{"total":142,"rows":[{"id":"2101.12176","title":"On the Origin of Implicit Regularization in Stochastic Gradient Descent","created":"2021-01-28","cited_by_count":184,"area":null},{"id":"2110.06914","title":"What Happens after SGD Reaches Zero Loss? --A Mathematical Framework","created":"2021-10-13","cited_by_count":107,"area":null},{"id":"2210.14199","title":"Same Pre-training Loss, Better Downstream: Implicit Bias Matters for Language Models","created":"2022-10-25","cited_by_count":84,"area":null},{"id":"2102.12470","title":"On the Validity of Modeling SGD with Stochastic Differential Equations (SDEs)","created":"2021-02-24","cited_by_count":73,"area":null},{"id":"2207.02628","title":"The alignment property of SGD noise and how it helps select flat minima: A stability analysis","created":"2022-07-06","cited_by_count":64,"area":null},{"id":"2105.13462","title":"On Linear Stability of SGD and Input-Smoothness of Neural Networks","created":"2021-05-27","cited_by_count":63,"area":null},{"id":"2109.14119","title":"Stochastic Training is Not Necessary for Generalization","created":"2021-09-29","cited_by_count":63,"area":null},{"id":"2105.02716","title":"Noether's Learning Dynamics: Role of Symmetry Breaking in Neural Networks","created":"2021-05-06","cited_by_count":50,"area":null},{"id":"2105.01650","title":"Stochastic gradient descent with noise of machine learning type. Part I: Discrete time analysis","created":"2021-05-04","cited_by_count":39,"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":"2303.02749","title":"Revisiting the Noise Model of Stochastic Gradient Descent","created":"2023-03-05","cited_by_count":36,"area":null},{"id":"2102.04396","title":"SGD in the Large: Average-case Analysis, Asymptotics, and Stepsize Criticality","created":"2021-02-08","cited_by_count":35,"area":null},{"id":"2107.06608","title":"Continuous vs. Discrete Optimization of Deep Neural Networks","created":"2021-07-14","cited_by_count":34,"area":null},{"id":"2105.09557","title":"Power-law escape rate of SGD","created":"2021-05-20","cited_by_count":29,"area":null},{"id":"2305.16038","title":"Implicit bias of SGD in $L_{2}$-regularized linear DNNs: One-way jumps from high to low rank","created":"2023-05-25","cited_by_count":29,"area":null},{"id":"2103.17182","title":"Positive-Negative Momentum: Manipulating Stochastic Gradient Noise to Improve Generalization","created":"2021-03-31","cited_by_count":28,"area":null},{"id":"2309.00079","title":"On the Implicit Bias of Adam","created":"2023-08-31","cited_by_count":27,"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":"2106.02588","title":"Stochastic gradient descent with noise of machine learning type. Part II: Continuous time analysis","created":"2021-06-04","cited_by_count":25,"area":null},{"id":"2302.00849","title":"Implicit regularization in Heavy-ball momentum accelerated stochastic gradient descent","created":"2023-02-02","cited_by_count":25,"area":null},{"id":"2103.04902","title":"Stochasticity helps to navigate rough landscapes: comparing gradient-descent-based algorithms in the phase retrieval problem","created":"2021-03-08","cited_by_count":23,"area":null},{"id":"2301.08203","title":"An SDE for Modeling SAM: Theory and Insights","created":"2023-01-19","cited_by_count":22,"area":null},{"id":"2405.14578","title":"Surge Phenomenon in Optimal Learning Rate and Batch Size Scaling","created":"2024-05-23","cited_by_count":22,"area":null},{"id":"2503.12811","title":"A Multi-Power Law for Loss Curve Prediction Across Learning Rate Schedules","created":"2025-03-17","cited_by_count":22,"area":null},{"id":"2507.02119","title":"Scaling Collapse Reveals Universal Dynamics in Compute-Optimally Trained Neural Networks","created":"2025-07-02","cited_by_count":22,"area":null},{"id":"2301.02312","title":"Training trajectories, mini-batch losses and the curious role of the learning rate","created":"2023-01-05","cited_by_count":21,"area":null},{"id":"2501.12666","title":"Explicit Eigenvalue Regularization Improves Sharpness-Aware Minimization","created":"2025-01-22","cited_by_count":21,"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":"2106.03696","title":"Dynamics of Stochastic Momentum Methods on Large-scale, Quadratic Models","created":"2021-06-07","cited_by_count":16,"area":null},{"id":"2101.06640","title":"Estimating informativeness of samples with Smooth Unique Information","created":"2021-01-17","cited_by_count":15,"area":null},{"id":"2105.13922","title":"Discretization Drift in Two-Player Games","created":"2021-05-28","cited_by_count":14,"area":null},{"id":"2405.20763","title":"Improving Generalization and Convergence by Enhancing Implicit Regularization","created":"2024-05-31","cited_by_count":14,"area":null},{"id":"2607.21716","title":"A Defense of the Quadratic Model","created":"2026-07-23","cited_by_count":14,"area":null},{"id":"2103.01338","title":"Acceleration via Fractal Learning Rate Schedules","created":"2021-03-01","cited_by_count":13,"area":null},{"id":"2111.06328","title":"Stationary Behavior of Constant Stepsize SGD Type Algorithms: An Asymptotic Characterization","created":"2021-11-11","cited_by_count":13,"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":"2102.07006","title":"Asymmetric Heavy Tails and Implicit Bias in Gaussian Noise Injections","created":"2021-02-13","cited_by_count":12,"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":"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":"2305.15850","title":"Stochastic Modified Equations and Dynamics of Dropout Algorithm","created":"2023-05-25","cited_by_count":11,"area":null},{"id":"2107.09437","title":"Edge of chaos as a guiding principle for modern neural network training","created":"2021-07-20","cited_by_count":10,"area":null},{"id":"2511.04622","title":"ODE approximation for the Adam algorithm: General and overparametrized setting","created":"2025-11-06","cited_by_count":10,"area":null},{"id":"2602.00170","title":"The Blessing of Dimensionality in LLM Fine-tuning: A Variance-Curvature Perspective","created":"2026-01-30","cited_by_count":10,"area":null},{"id":"2604.14108","title":"Momentum Further Constrains Sharpness at the Edge of Stochastic Stability","created":"2026-04-15","cited_by_count":10,"area":null},{"id":"2105.01303","title":"Personalized Algorithm Generation: A Case Study in Learning ODE Integrators","created":"2021-05-04","cited_by_count":9,"area":null},{"id":"2108.03947","title":"On the Hyperparameters in Stochastic Gradient Descent with Momentum","created":"2021-08-09","cited_by_count":9,"area":null},{"id":"2301.13703","title":"Dissecting the Effects of SGD Noise in Distinct Regimes of Deep Learning","created":"2023-01-31","cited_by_count":9,"area":null},{"id":"2602.01480","title":"Rod Flow: A Continuous-Time Model for Gradient Descent at the Edge of Stability","created":"2026-02-01","cited_by_count":9,"area":null},{"id":"2110.05960","title":"Imitating Deep Learning Dynamics via Locally Elastic Stochastic Differential Equations","created":"2021-10-11","cited_by_count":8,"area":null},{"id":"2407.20209","title":"Characterizing Dynamical Stability of Stochastic Gradient Descent in Overparameterized Learning","created":"2024-07-29","cited_by_count":8,"area":null},{"id":"2602.06797","title":"Optimal Learning Rate Schedules under Functional Scaling Laws: Power Decay and Warmup-Stable-Decay","created":"2026-02-06","cited_by_count":8,"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":"2302.07125","title":"Stochastic Modified Flows, Mean-Field Limits and Dynamics of Stochastic Gradient Descent","created":"2023-02-14","cited_by_count":7,"area":null},{"id":"2303.15634","title":"Learning Rate Schedules in the Presence of Distribution Shift","created":"2023-03-27","cited_by_count":7,"area":null},{"id":"2406.11733","title":"To Clip or not to Clip: the Dynamics of SGD with Gradient Clipping in High-Dimensions","created":"2024-06-17","cited_by_count":7,"area":null},{"id":"2407.16427","title":"Stochastic weight matrix dynamics during learning and Dyson Brownian motion","created":"2024-07-23","cited_by_count":7,"area":null},{"id":"2411.09734","title":"Modeling AdaGrad, RMSProp, and Adam with Integro-Differential Equations","created":"2024-11-14","cited_by_count":7,"area":null},{"id":"2606.29554","title":"Optimizer Memory Makes Shuffle Order a First-Order Source of Fine-Tuning Noise","created":"2026-06-28","cited_by_count":7,"area":null},{"id":"2207.04922","title":"On uniform-in-time diffusion approximation for stochastic gradient descent","created":"2022-07-11","cited_by_count":6,"area":null},{"id":"2401.11600","title":"Understanding the Generalization Benefits of Late Learning Rate Decay","created":"2024-01-21","cited_by_count":6,"area":null},{"id":"2402.12508","title":"SDEs for Minimax Optimization","created":"2024-02-19","cited_by_count":6,"area":null},{"id":"2502.02132","title":"How Memory in Optimization Algorithms Implicitly Modifies the Loss","created":"2025-02-04","cited_by_count":6,"area":null},{"id":"2112.00987","title":"On Large Batch Training and Sharp Minima: A Fokker-Planck Perspective","created":"2021-12-02","cited_by_count":5,"area":null},{"id":"2205.13799","title":"Generalization Bounds for Gradient Methods via Discrete and Continuous Prior","created":"2022-05-27","cited_by_count":5,"area":null},{"id":"2502.17009","title":"Unbiased and Sign Compression in Distributed Learning: Comparing Noise Resilience via SDEs","created":"2025-02-24","cited_by_count":5,"area":null},{"id":"2105.08037","title":"Adversarial Training for Gradient Descent: Analysis Through its Continuous-time Approximation","created":"2021-05-17","cited_by_count":4,"area":null},{"id":"2109.09833","title":"Revisiting the Characteristics of Stochastic Gradient Noise and Dynamics","created":"2021-09-20","cited_by_count":4,"area":null},{"id":"2202.04509","title":"Optimal learning rate schedules in high-dimensional non-convex optimization problems","created":"2022-02-09","cited_by_count":4,"area":null},{"id":"2311.00235","title":"Implicit biases in multitask and continual learning from a backward error analysis perspective","created":"2023-11-01","cited_by_count":4,"area":null},{"id":"2406.00396","title":"Stochastic Resetting Mitigates Latent Gradient Bias of SGD from Label Noise","created":"2024-06-01","cited_by_count":4,"area":null},{"id":"2506.00181","title":"On the Interaction of Batch Noise, Adaptivity, and Compression, under $(L_0,L_1)$-Smoothness: An SDE Approach","created":"2025-05-30","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":"2306.02618","title":"Enhance Diffusion to Improve Robust Generalization","created":"2023-06-05","cited_by_count":3,"area":null},{"id":"2505.19537","title":"Continuous-Time Analysis of Heavy Ball Momentum in Min-Max Games","created":"2025-05-26","cited_by_count":3,"area":null},{"id":"2508.00180","title":"EMA Without the Lag: Bias-Corrected Iterate Averaging Schemes","created":"2025-07-31","cited_by_count":3,"area":null},{"id":"2105.03788","title":"Dynamic Game Theoretic Neural Optimizer","created":"2021-05-08","cited_by_count":2,"area":null},{"id":"2108.09507","title":"Shift-Curvature, SGD, and Generalization","created":"2021-08-21","cited_by_count":2,"area":null},{"id":"2210.07513","title":"Continuous-in-time Limit for Bayesian Bandits","created":"2022-10-14","cited_by_count":2,"area":null},{"id":"2302.00766","title":"Privacy Risk for anisotropic Langevin dynamics using relative entropy bounds","created":"2023-02-01","cited_by_count":2,"area":null},{"id":"2309.04557","title":"Regret-Optimal Federated Transfer Learning for Kernel Regression with Applications in American Option Pricing","created":"2023-09-08","cited_by_count":2,"area":null},{"id":"2401.12332","title":"A Precise Characterization of SGD Stability Using Loss Surface Geometry","created":"2024-01-22","cited_by_count":2,"area":null},{"id":"2402.03467","title":"Stochastic Modified Flows for Riemannian Stochastic Gradient Descent","created":"2024-02-02","cited_by_count":2,"area":null},{"id":"2407.19353","title":"Spring-block theory of feature learning in deep neural networks","created":"2024-07-28","cited_by_count":2,"area":null},{"id":"2509.18001","title":"Unveiling m-Sharpness Through the Structure of Stochastic Gradient Noise","created":"2025-09-22","cited_by_count":2,"area":null},{"id":"2601.16563","title":"Process-Tensor Tomography of SGD: Measuring Non-Markovian Memory via Back-Flow of Distinguishability","created":"2026-01-23","cited_by_count":2,"area":null},{"id":"2602.05600","title":"On the Superlinear Relationship between SGD Noise Covariance and Loss Landscape Curvature","created":"2026-02-05","cited_by_count":2,"area":null},{"id":"2603.03226","title":"Adaptive Methods Are Preferable in High Privacy Settings: An SDE Perspective","created":"2026-03-03","cited_by_count":2,"area":null},{"id":"2105.02062","title":"Understanding Short-Range Memory Effects in Deep Neural Networks","created":"2021-05-05","cited_by_count":1,"area":null},{"id":"2203.11992","title":"Resonance in Weight Space: Covariate Shift Can Drive Divergence of SGD with Momentum","created":"2022-03-22","cited_by_count":1,"area":null},{"id":"2210.11257","title":"A note on diffusion limits for stochastic gradient descent","created":"2022-10-20","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":"2310.13901","title":"Towards Hyperparameter-Agnostic DNN Training via Dynamical System Insights","created":"2023-10-21","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":"2406.11159","title":"Distributed Stochastic Gradient Descent with Staleness: A Stochastic Delay Differential Equation Based Framework","created":"2024-06-17","cited_by_count":1,"area":null},{"id":"2410.17297","title":"Error estimates between SGD with momentum and underdamped Langevin diffusion","created":"2024-10-22","cited_by_count":1,"area":null},{"id":"2505.15303","title":"Laplace Sample Information: Data Informativeness Through a Bayesian Lens","created":"2025-05-21","cited_by_count":1,"area":null},{"id":"2509.21614","title":"Effective continuous equations for adaptive SGD: a stochastic analysis view","created":"2025-09-25","cited_by_count":1,"area":null},{"id":"2601.10962","title":"Noise-Driven Exploration and Transient Freezing Select Flat Minima in Stochastic Gradient Descent","created":"2026-01-16","cited_by_count":1,"area":null},{"id":"2602.05393","title":"Late-to-Early Training: LET LLMs Learn Earlier, So Faster and Better","created":"2026-02-05","cited_by_count":1,"area":null}],"next_cursor":"100"}