{"total":68,"rows":[{"id":"2210.06313","title":"The Lazy Neuron Phenomenon: On Emergence of Activation Sparsity in Transformers","created":"2022-10-12","cited_by_count":122,"area":null},{"id":"2302.07011","title":"A Modern Look at the Relationship between Sharpness and Generalization","created":"2023-02-14","cited_by_count":92,"area":null},{"id":"2310.04415","title":"Why Do We Need Weight Decay in Modern Deep Learning?","created":"2023-10-06","cited_by_count":72,"area":null},{"id":"2212.07469","title":"Learning threshold neurons via the \"edge of stability\"","created":"2022-12-14","cited_by_count":51,"area":null},{"id":"2305.11788","title":"Implicit Bias of Gradient Descent for Logistic Regression at the Edge of Stability","created":"2023-05-19","cited_by_count":42,"area":null},{"id":"2307.06440","title":"No Train No Gain: Revisiting Efficient Training Algorithms For Transformer-based Language Models","created":"2023-07-12","cited_by_count":41,"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":"2302.08982","title":"(S)GD over Diagonal Linear Networks: Implicit Regularisation, Large Stepsizes and Edge of Stability","created":"2023-02-17","cited_by_count":36,"area":null},{"id":"2402.15926","title":"Large Stepsize Gradient Descent for Logistic Loss: Non-Monotonicity of the Loss Improves Optimization Efficiency","created":"2024-02-24","cited_by_count":35,"area":null},{"id":"2211.06506","title":"Spectral Evolution and Invariance in Linear-width Neural Networks","created":"2022-11-11","cited_by_count":30,"area":null},{"id":"2310.07269","title":"Why Does Sharpness-Aware Minimization Generalize Better Than SGD?","created":"2023-10-11","cited_by_count":28,"area":null},{"id":"2309.17230","title":"Spurious Feature Diversification Improves Out-of-distribution Generalization","created":"2023-09-29","cited_by_count":26,"area":null},{"id":"2307.06966","title":"Layer-wise Linear Mode Connectivity","created":"2023-07-13","cited_by_count":22,"area":null},{"id":"2310.01687","title":"From Stability to Chaos: Analyzing Gradient Descent Dynamics in Quadratic Regression","created":"2023-10-02","cited_by_count":17,"area":null},{"id":"2405.16642","title":"Fast TRAC: A Parameter-Free Optimizer for Lifelong Reinforcement Learning","created":"2024-05-26","cited_by_count":17,"area":"deeprl"},{"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":"2502.03435","title":"Taking a Big Step: Large Learning Rates in Denoising Score Matching Prevent Memorization","created":"2025-02-05","cited_by_count":17,"area":"diffusion"},{"id":"2305.12133","title":"Loss Spike in Training Neural Networks","created":"2023-05-20","cited_by_count":16,"area":null},{"id":"2403.09053","title":"Towards a theory of model distillation","created":"2024-03-14","cited_by_count":15,"area":null},{"id":"2212.07346","title":"Learning useful representations for shifting tasks and distributions","created":"2022-12-14","cited_by_count":14,"area":null},{"id":"2310.11428","title":"Butterfly Effects of SGD Noise: Error Amplification in Behavior Cloning and Autoregression","created":"2023-10-17","cited_by_count":14,"area":null},{"id":"2502.02496","title":"Deep Weight Factorization: Sparse Learning Through the Lens of Artificial Symmetries","created":"2025-02-04","cited_by_count":14,"area":null},{"id":"2309.10688","title":"On the different regimes of Stochastic Gradient Descent","created":"2023-09-19","cited_by_count":12,"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":"2605.02105","title":"Sharpness-Aware Pretraining Mitigates Catastrophic Forgetting","created":"2026-05-04","cited_by_count":10,"area":null},{"id":"2505.11846","title":"Learning on a Razor's Edge: Identifiability and Singularity of Polynomial Neural Networks","created":"2025-05-17","cited_by_count":9,"area":null},{"id":"2602.05846","title":"Optimal scaling laws in learning hierarchical multi-index models","created":"2026-02-05","cited_by_count":9,"area":null},{"id":"2301.07737","title":"Catapult Dynamics and Phase Transitions in Quadratic Nets","created":"2023-01-18","cited_by_count":8,"area":null},{"id":"2502.09297","title":"When Do Neural Networks Learn World Models?","created":"2025-02-13","cited_by_count":8,"area":"wm"},{"id":"2211.11623","title":"Linear Stability Hypothesis and Rank Stratification for Nonlinear Models","created":"2022-11-21","cited_by_count":7,"area":null},{"id":"2309.03004","title":"A Theoretical Explanation of Activation Sparsity through Flat Minima and Adversarial Robustness","created":"2023-09-06","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":"2504.04105","title":"Minimax Optimal Convergence of Gradient Descent in Logistic Regression via Large and Adaptive Stepsizes","created":"2025-04-05","cited_by_count":7,"area":null},{"id":"2509.00454","title":"Universal Properties of Activation Sparsity in Modern Large Language Models","created":"2025-08-30","cited_by_count":7,"area":null},{"id":"2509.25351","title":"Gradient Descent with Large Step Sizes: Chaos and Fractal Convergence Region","created":"2025-09-29","cited_by_count":7,"area":null},{"id":"2302.02904","title":"Rethinking Gauss-Newton for learning over-parameterized models","created":"2023-02-06","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":"2410.22113","title":"Where Do Large Learning Rates Lead Us?","created":"2024-10-29","cited_by_count":6,"area":null},{"id":"2507.12837","title":"Understanding the Evolution of the Neural Tangent Kernel at the Edge of Stability","created":"2025-07-17","cited_by_count":6,"area":null},{"id":"2604.13627","title":"(How) Learning Rates Regulate Catastrophic Overtraining","created":"2026-04-15","cited_by_count":6,"area":null},{"id":"2307.08921","title":"Optimistic Estimate Uncovers the Potential of Nonlinear Models","created":"2023-07-18","cited_by_count":5,"area":null},{"id":"2410.05612","title":"A Bayesian Model Selection Criterion for Selecting Pretraining Checkpoints","created":"2024-10-08","cited_by_count":5,"area":null},{"id":"2402.07875","title":"Implicit Bias of Policy Gradient in Linear Quadratic Control: Extrapolation to Unseen Initial States","created":"2024-02-12","cited_by_count":4,"area":"deeprl"},{"id":"2410.16401","title":"Simplicity Bias via Global Convergence of Sharpness Minimization","created":"2024-10-21","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":"2311.17539","title":"Critical Influence of Overparameterization on Sharpness-aware Minimization","created":"2023-11-29","cited_by_count":3,"area":null},{"id":"2403.00946","title":"Fine-tuning with Very Large Dropout","created":"2024-03-01","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":"2407.03848","title":"Bias of Stochastic Gradient Descent or the Architecture: Disentangling the Effects of Overparameterization of Neural Networks","created":"2024-07-04","cited_by_count":2,"area":null},{"id":"2507.17748","title":"Large Learning Rates Simultaneously Achieve Robustness to Spurious Correlations and Compressibility","created":"2025-07-23","cited_by_count":2,"area":null},{"id":"2510.04686","title":"How does the optimizer implicitly bias the model merging loss landscape?","created":"2025-10-06","cited_by_count":2,"area":null},{"id":"2510.21020","title":"From Information to Generative Exponent: Learning Rate Induces Phase Transitions in SGD","created":"2025-10-23","cited_by_count":2,"area":null},{"id":"2305.13141","title":"Tight conditions for when the NTK approximation is valid","created":"2023-05-22","cited_by_count":1,"area":null},{"id":"2311.11303","title":"Large Learning Rates Improve Generalization: But How Large Are We Talking About?","created":"2023-11-19","cited_by_count":1,"area":null},{"id":"2506.18221","title":"These Are Not All the Features You Are Looking For: A Fundamental Bottleneck in Supervised Pretraining","created":"2025-06-23","cited_by_count":1,"area":null},{"id":"2604.02653","title":"Product-Stability: Provable Convergence for Gradient Descent on the Edge of Stability","created":"2026-04-03","cited_by_count":1,"area":null},{"id":"2605.21292","title":"Unbiased Gradients, Moving Stability Boundaries: Exact Mini-Batch Geometry in Linear Self-Attention","created":"2026-05-20","cited_by_count":1,"area":null},{"id":"2606.31282","title":"Revisiting the Volume Hypothesis","created":"2026-06-30","cited_by_count":1,"area":null},{"id":"2404.16317","title":"FLAASH: Flexible Accelerator Architecture for Sparse High-Order Tensor Contraction","created":"2024-04-25","cited_by_count":0,"area":null},{"id":"2412.17613","title":"Can Stability be Detrimental? Better Generalization through Gradient Descent Instabilities","created":"2024-12-23","cited_by_count":0,"area":null},{"id":"2604.06366","title":"Stochastic Gradient Descent in the Saddle-to-Saddle Regime of Deep Linear Networks","created":"2026-04-07","cited_by_count":0,"area":null},{"id":"2604.16809","title":"A Mechanism Study of Delayed Loss Spikes in Batch-Normalized Linear Models","created":"2026-04-18","cited_by_count":0,"area":null},{"id":"2605.25612","title":"Towards the Connection between Activation Sparsity and Flat Minima","created":"2026-05-25","cited_by_count":0,"area":null},{"id":"2606.28464","title":"Singular Learning and Occam's Razor in Deep Monomial Networks","created":"2026-06-26","cited_by_count":0,"area":null},{"id":"2607.26059","title":"Emergent Sparsity in Frozen Random CNN Feature Extractors for Deep Reinforcement Learning","created":"2026-05-15","cited_by_count":0,"area":"deeprl"},{"id":"2610.06120","title":"Mind the Drift: Diagonal Linear Networks Under Large Learning Rates","created":"2026-10-05","cited_by_count":0,"area":null},{"id":"2610.16868","title":"From Parallel to Sequential: Small-Batch Noise Restores Simplicity Bias of Muon","created":"2026-10-12","cited_by_count":0,"area":null}],"next_cursor":null}