{"total":146,"rows":[{"id":"2103.00065","title":"Gradient Descent on Neural Networks Typically Occurs at the Edge of Stability","created":"2021-02-26","cited_by_count":427,"area":null},{"id":"2110.09348","title":"Understanding Dimensional Collapse in Contrastive Self-supervised Learning","created":"2021-10-18","cited_by_count":378,"area":null},{"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":"2205.09745","title":"Understanding Gradient Descent on Edge of Stability in Deep Learning","created":"2022-05-19","cited_by_count":128,"area":null},{"id":"2110.08529","title":"Sharpness-Aware Minimization Improves Language Model Generalization","created":"2021-10-16","cited_by_count":108,"area":null},{"id":"2206.07085","title":"Understanding the Generalization Benefit of Normalization Layers: Sharpness Reduction","created":"2022-06-14","cited_by_count":86,"area":null},{"id":"2208.12591","title":"On the Implicit Bias in Deep-Learning Algorithms","created":"2022-08-26","cited_by_count":86,"area":null},{"id":"2402.18762","title":"Disentangling the Causes of Plasticity Loss in Neural Networks","created":"2024-02-29","cited_by_count":86,"area":"deeprl"},{"id":"2109.14119","title":"Stochastic Training is Not Necessary for Generalization","created":"2021-09-29","cited_by_count":63,"area":null},{"id":"2407.01800","title":"Normalization and effective learning rates in reinforcement learning","created":"2024-07-01","cited_by_count":58,"area":"deeprl"},{"id":"2303.03108","title":"Gradient Norm Aware Minimization Seeks First-Order Flatness and Improves Generalization","created":"2023-03-03","cited_by_count":57,"area":null},{"id":"2210.01513","title":"The Dynamics of Sharpness-Aware Minimization: Bouncing Across Ravines and Drifting Towards Wide Minima","created":"2022-10-04","cited_by_count":51,"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":"2305.17490","title":"The Implicit Regularization of Dynamical Stability in Stochastic Gradient Descent","created":"2023-05-27","cited_by_count":44,"area":null},{"id":"2111.12229","title":"Subspace Adversarial Training","created":"2021-11-24","cited_by_count":41,"area":null},{"id":"2507.07101","title":"Small Batch Size Training for Language Models: When Vanilla SGD Works, and Why Gradient Accumulation Is Wasteful","created":"2025-07-09","cited_by_count":41,"area":null},{"id":"2209.13083","title":"Why neural networks find simple solutions: the many regularizers of geometric complexity","created":"2022-09-27","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":"2305.16292","title":"Sharpness-Aware Minimization Leads to Low-Rank Features","created":"2023-05-25","cited_by_count":38,"area":null},{"id":"2301.12832","title":"Deep networks for system identification: a Survey","created":"2023-01-30","cited_by_count":37,"area":null},{"id":"2309.15639","title":"Enhancing Sharpness-Aware Optimization Through Variance Suppression","created":"2023-09-27","cited_by_count":37,"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":"2307.07873","title":"Why Does Little Robustness Help? A Further Step Towards Understanding Adversarial Transferability","created":"2023-07-15","cited_by_count":32,"area":null},{"id":"2308.07870","title":"Brain-inspired Computational Intelligence via Predictive Coding","created":"2023-08-15","cited_by_count":30,"area":null},{"id":"2106.13897","title":"Implicit Gradient Alignment in Distributed and Federated Learning","created":"2021-06-25","cited_by_count":29,"area":null},{"id":"2604.21691","title":"There Will Be a Scientific Theory of Deep Learning","created":"2026-04-23","cited_by_count":29,"area":null},{"id":"2307.11108","title":"Flatness-Aware Minimization for Domain Generalization","created":"2023-07-20","cited_by_count":27,"area":null},{"id":"2309.00079","title":"On the Implicit Bias of Adam","created":"2023-08-31","cited_by_count":27,"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":"2207.05952","title":"Implicit regularization of dropout","created":"2022-07-13","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":"2207.02099","title":"An Empirical Study of Implicit Regularization in Deep Offline RL","created":"2022-07-05","cited_by_count":24,"area":"offlinerl"},{"id":"2206.07252","title":"Implicit Regularization or Implicit Conditioning? Exact Risk Trajectories of SGD in High Dimensions","created":"2022-06-15","cited_by_count":23,"area":null},{"id":"2501.12666","title":"Explicit Eigenvalue Regularization Improves Sharpness-Aware Minimization","created":"2025-01-22","cited_by_count":21,"area":null},{"id":"2306.11197","title":"Sparse Modular Activation for Efficient Sequence Modeling","created":"2023-06-19","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":"2209.03695","title":"Training Scale-Invariant Neural Networks on the Sphere Can Happen in Three Regimes","created":"2022-09-08","cited_by_count":19,"area":null},{"id":"2406.08654","title":"Large Stepsize Gradient Descent for Non-Homogeneous Two-Layer Networks: Margin Improvement and Fast Optimization","created":"2024-06-12","cited_by_count":17,"area":null},{"id":"2210.02720","title":"Understanding Gradient Regularization in Deep Learning: Efficient Finite-Difference Computation and Implicit Bias","created":"2022-10-06","cited_by_count":16,"area":null},{"id":"2306.17499","title":"The Implicit Bias of Minima Stability in Multivariate Shallow ReLU Networks","created":"2023-06-30","cited_by_count":15,"area":null},{"id":"2510.06213","title":"Training Dynamics Impact Post-Training Quantization Robustness","created":"2025-10-07","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":"2206.02126","title":"Learning Dynamics and Generalization in Reinforcement Learning","created":"2022-06-05","cited_by_count":14,"area":null},{"id":"2306.05651","title":"Differentially Private Sharpness-Aware Training","created":"2023-06-09","cited_by_count":14,"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":"2505.24022","title":"The Rich and the Simple: On the Implicit Bias of Adam and SGD","created":"2025-05-29","cited_by_count":13,"area":null},{"id":"2210.00272","title":"FINDE: Neural Differential Equations for Finding and Preserving Invariant Quantities","created":"2022-10-01","cited_by_count":12,"area":null},{"id":"2401.10809","title":"Neglected Hessian component explains mysteries in Sharpness regularization","created":"2024-01-19","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":"2502.06604","title":"Do we really have to filter out random noise in pre-training data for language models?","created":"2025-02-10","cited_by_count":11,"area":null},{"id":"2205.15142","title":"Special Properties of Gradient Descent with Large Learning Rates","created":"2022-05-30","cited_by_count":10,"area":null},{"id":"2306.15308","title":"Machine learning in solar physics","created":"2023-06-27","cited_by_count":10,"area":null},{"id":"2410.14802","title":"Implicit Regularization of Sharpness-Aware Minimization for Scale-Invariant Problems","created":"2024-10-18","cited_by_count":10,"area":null},{"id":"2502.20566","title":"Stochastic Rounding for LLM Training: Theory and Practice","created":"2025-02-27","cited_by_count":10,"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":"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":"2210.10452","title":"Rethinking Sharpness-Aware Minimization as Variational Inference","created":"2022-10-19","cited_by_count":8,"area":null},{"id":"2304.11446","title":"Fast Diffusion Probabilistic Model Sampling through the lens of Backward Error Analysis","created":"2023-04-22","cited_by_count":8,"area":"diffusion"},{"id":"2507.01098","title":"Proof of a perfect platonic representation hypothesis","created":"2025-07-01","cited_by_count":8,"area":null},{"id":"2507.20057","title":"What Can Grokking Teach Us About Learning Under Nonstationarity?","created":"2025-07-26","cited_by_count":8,"area":null},{"id":"2111.15090","title":"The Geometric Occam's Razor Implicit in Deep Learning","created":"2021-11-30","cited_by_count":7,"area":null},{"id":"2202.05352","title":"Domain Adversarial Training: A Game Perspective","created":"2022-02-10","cited_by_count":7,"area":null},{"id":"2303.17940","title":"Per-Example Gradient Regularization Improves Learning Signals from Noisy Data","created":"2023-03-31","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":"2305.19243","title":"Improving Generalization of Complex Models under Unbounded Loss Using PAC-Bayes Bounds","created":"2023-05-30","cited_by_count":6,"area":null},{"id":"2409.06142","title":"Variational Search Distributions","created":"2024-09-10","cited_by_count":6,"area":null},{"id":"2410.14837","title":"Topological obstruction to the training of shallow ReLU neural networks","created":"2024-10-18","cited_by_count":6,"area":null},{"id":"2410.22113","title":"Where Do Large Learning Rates Lead Us?","created":"2024-10-29","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":"2604.20446","title":"The Origin of Edge of Stability","created":"2026-04-22","cited_by_count":6,"area":null},{"id":"2112.08916","title":"GOSH: Task Scheduling Using Deep Surrogate Models in Fog Computing Environments","created":"2021-12-16","cited_by_count":5,"area":null},{"id":"2304.12579","title":"Learning Trajectories are Generalization Indicators","created":"2023-04-25","cited_by_count":5,"area":null},{"id":"2309.02082","title":"Backward error analysis and the qualitative behaviour of stochastic optimization algorithms: Application to stochastic coordinate descent","created":"2023-09-05","cited_by_count":5,"area":null},{"id":"2604.16242","title":"Detecting and Suppressing Reward Hacking with Gradient Fingerprints","created":"2026-04-17","cited_by_count":5,"area":"alignment"},{"id":"2205.10697","title":"Lassoed Tree Boosting","created":"2022-05-22","cited_by_count":4,"area":null},{"id":"2205.12642","title":"On the Interpretability of Regularisation for Neural Networks Through Model Gradient Similarity","created":"2022-05-25","cited_by_count":4,"area":null},{"id":"2206.14853","title":"Fairness via In-Processing in the Over-parameterized Regime: A Cautionary Tale","created":"2022-06-29","cited_by_count":4,"area":null},{"id":"2306.00342","title":"Combining Explicit and Implicit Regularization for Efficient Learning in Deep Networks","created":"2023-06-01","cited_by_count":4,"area":null},{"id":"2306.11903","title":"Deep Fusion: Efficient Network Training via Pre-trained Initializations","created":"2023-06-20","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":"2405.15706","title":"The Impact of Geometric Complexity on Neural Collapse in Transfer Learning","created":"2024-05-24","cited_by_count":4,"area":null},{"id":"2409.05800","title":"Input Space Mode Connectivity in Deep Neural Networks","created":"2024-09-09","cited_by_count":4,"area":null},{"id":"2410.00232","title":"Preconditioning for Accelerated Gradient Descent Optimization and Regularization","created":"2024-09-30","cited_by_count":4,"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":"2602.01642","title":"The Effect of Mini-Batch Noise on the Implicit Bias of Adam","created":"2026-02-02","cited_by_count":4,"area":null},{"id":"2310.10006","title":"Soft ascent-descent as a stable and flexible alternative to flooding","created":"2023-10-16","cited_by_count":3,"area":null},{"id":"2310.12977","title":"Training Dynamics of Deep Network Linear Regions","created":"2023-10-19","cited_by_count":3,"area":null},{"id":"2311.06138","title":"Minimum norm interpolation by perceptra: Explicit regularization and implicit bias","created":"2023-11-10","cited_by_count":3,"area":null},{"id":"2311.15051","title":"Gradient Descent with Polyak's Momentum Finds Flatter Minima via Large Catapults","created":"2023-11-25","cited_by_count":3,"area":null},{"id":"2406.09723","title":"When Will Gradient Regularization Be Harmful?","created":"2024-06-14","cited_by_count":3,"area":null},{"id":"2505.11434","title":"Controlling the Flow: Stability and Convergence for Stochastic Gradient Descent with Decaying Regularization","created":"2025-05-16","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":"2110.14254","title":"Multilayer Lookahead: a Nested Version of Lookahead","created":"2021-10-27","cited_by_count":2,"area":null},{"id":"2211.09639","title":"Why Deep Learning Generalizes","created":"2022-11-17","cited_by_count":2,"area":null},{"id":"2211.15853","title":"Disentangling the Mechanisms Behind Implicit Regularization in SGD","created":"2022-11-29","cited_by_count":2,"area":null},{"id":"2307.05789","title":"Implicit regularisation in stochastic gradient descent: from single-objective to two-player games","created":"2023-07-11","cited_by_count":2,"area":null},{"id":"2309.01796","title":"Implicit Regularization Makes Overparameterized Asymmetric Matrix Sensing Robust to Perturbations","created":"2023-09-04","cited_by_count":2,"area":null},{"id":"2405.18590","title":"A Margin-based Multiclass Generalization Bound via Geometric Complexity","created":"2024-05-28","cited_by_count":2,"area":null},{"id":"2410.12025","title":"Geometric Inductive Biases of Deep Networks: The Role of Data and Architecture","created":"2024-10-15","cited_by_count":2,"area":null}],"next_cursor":"100"}