{"total":83,"rows":[{"id":"2209.15594","title":"Self-Stabilization: The Implicit Bias of Gradient Descent at the Edge of Stability","created":"2022-09-30","cited_by_count":155,"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":"2208.12591","title":"On the Implicit Bias in Deep-Learning Algorithms","created":"2022-08-26","cited_by_count":86,"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":"2311.18817","title":"Dichotomy of Early and Late Phase Implicit Biases Can Provably Induce Grokking","created":"2023-11-30","cited_by_count":80,"area":null},{"id":"2503.10622","title":"Transformers without Normalization","created":"2025-03-13","cited_by_count":70,"area":null},{"id":"2211.05729","title":"How Does Sharpness-Aware Minimization Minimize Sharpness?","created":"2022-11-10","cited_by_count":65,"area":null},{"id":"2207.12678","title":"Analyzing Sharpness along GD Trajectory: Progressive Sharpening and Edge of Stability","created":"2022-07-26","cited_by_count":63,"area":null},{"id":"2302.10911","title":"Revisiting Weighted Aggregation in Federated Learning with Neural Networks","created":"2023-02-14","cited_by_count":58,"area":null},{"id":"2210.03294","title":"Understanding Edge-of-Stability Training Dynamics with a Minimalist Example","created":"2022-10-07","cited_by_count":56,"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":"2301.11500","title":"Understanding Incremental Learning of Gradient Descent: A Fine-grained Analysis of Matrix Sensing","created":"2023-01-27","cited_by_count":42,"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":"2307.11007","title":"Sharpness Minimization Algorithms Do Not Only Minimize Sharpness To Achieve Better Generalization","created":"2023-07-20","cited_by_count":39,"area":null},{"id":"2405.16002","title":"Does SGD really happen in tiny subspaces?","created":"2024-05-25","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":"2306.04226","title":"Normalization Layers Are All That Sharpness-Aware Minimization Needs","created":"2023-06-07","cited_by_count":27,"area":null},{"id":"2307.04204","title":"Trajectory Alignment: Understanding the Edge of Stability Phenomenon via Bifurcation Theory","created":"2023-07-09","cited_by_count":26,"area":null},{"id":"2310.17087","title":"Good regularity creates large learning rate implicit biases: edge of stability, balancing, and catapult","created":"2023-10-26","cited_by_count":25,"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":"2410.23922","title":"Analyzing & Reducing the Need for Learning Rate Warmup in GPT Training","created":"2024-10-31","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":"2305.13064","title":"Gradient Descent Monotonically Decreases the Sharpness of Gradient Flow Solutions in Scalar Networks and Beyond","created":"2023-05-22","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":"2307.15196","title":"The Marginal Value of Momentum for Small Learning Rate SGD","created":"2023-07-27","cited_by_count":18,"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":"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":"2302.07384","title":"The Geometry of Neural Nets' Parameter Spaces Under Reparametrization","created":"2023-02-14","cited_by_count":16,"area":null},{"id":"2305.12133","title":"Loss Spike in Training Neural Networks","created":"2023-05-20","cited_by_count":16,"area":null},{"id":"2308.09543","title":"Latent State Models of Training Dynamics","created":"2023-08-18","cited_by_count":16,"area":null},{"id":"2211.13723","title":"Beyond Losses Reweighting: Empowering Multi-Task Learning via the Generalization Perspective","created":"2022-11-24","cited_by_count":15,"area":null},{"id":"2312.00379","title":"Optimal Sample Complexity of Contrastive Learning","created":"2023-12-01","cited_by_count":15,"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":"2406.03682","title":"A Universal Class of Sharpness-Aware Minimization Algorithms","created":"2024-06-06","cited_by_count":14,"area":null},{"id":"2305.18399","title":"On the impact of activation and normalization in obtaining isometric embeddings at initialization","created":"2023-05-28","cited_by_count":13,"area":null},{"id":"2505.02809","title":"Towards Quantifying the Hessian Structure of Neural Networks","created":"2025-05-05","cited_by_count":13,"area":null},{"id":"2506.04805","title":"Adaptive Preconditioners Trigger Loss Spikes in Adam","created":"2025-06-05","cited_by_count":13,"area":null},{"id":"2512.10938","title":"Stronger Normalization-Free Transformers","created":"2025-12-11","cited_by_count":13,"area":null},{"id":"2403.06392","title":"Towards Robust Out-of-Distribution Generalization Bounds via Sharpness","created":"2024-03-11","cited_by_count":11,"area":null},{"id":"2602.04998","title":"Learning Rate Matters: Vanilla LoRA May Suffice for LLM Fine-tuning","created":"2026-02-04","cited_by_count":10,"area":null},{"id":"2406.01255","title":"On the Nonlinearity of Layer Normalization","created":"2024-06-03","cited_by_count":9,"area":null},{"id":"2305.14683","title":"On progressive sharpening, flat minima and generalisation","created":"2023-05-24","cited_by_count":7,"area":null},{"id":"2305.16573","title":"Exploring Weight Balancing on Long-Tailed Recognition Problem","created":"2023-05-26","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":"2306.13239","title":"The Inductive Bias of Flatness Regularization for Deep Matrix Factorization","created":"2023-06-22","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":"2310.14423","title":"A Quadratic Synchronization Rule for Distributed Deep Learning","created":"2023-10-22","cited_by_count":5,"area":null},{"id":"2311.14387","title":"Achieving Margin Maximization Exponentially Fast via Progressive Norm Rescaling","created":"2023-11-24","cited_by_count":4,"area":null},{"id":"2410.16401","title":"Simplicity Bias via Global Convergence of Sharpness Minimization","created":"2024-10-21","cited_by_count":4,"area":null},{"id":"2411.05746","title":"Continuous-Time Analysis of Adaptive Optimization and Normalization","created":"2024-11-08","cited_by_count":4,"area":null},{"id":"2503.02809","title":"A Minimalist Example of Edge-of-Stability and Progressive Sharpening","created":"2025-03-04","cited_by_count":4,"area":null},{"id":"2503.21708","title":"On the Mathematical Relationship Between Layer Normalization and Dynamic Activation Functions","created":"2025-03-27","cited_by_count":4,"area":null},{"id":"2511.03548","title":"Flat Minima and Generalization: Insights from Stochastic Convex Optimization","created":"2025-11-05","cited_by_count":4,"area":null},{"id":"2302.12444","title":"On the Training Instability of Shuffling SGD with Batch Normalization","created":"2023-02-24","cited_by_count":3,"area":null},{"id":"2406.20006","title":"On the Trade-off between Flatness and Optimization in Distributed Learning","created":"2024-06-28","cited_by_count":3,"area":null},{"id":"2606.18080","title":"Edge Flow: A Tractable and Predictive Continuous-Time Model for Gradient Descent at the Edge of Stability","created":"2026-06-16","cited_by_count":3,"area":null},{"id":"2308.09565","title":"Understanding the Role of Layer Normalization in Label-Skewed Federated Learning","created":"2023-08-18","cited_by_count":2,"area":null},{"id":"2403.01420","title":"The Implicit Bias of Heterogeneity towards Invariance: A Study of Multi-Environment Matrix Sensing","created":"2024-03-03","cited_by_count":2,"area":null},{"id":"2404.00521","title":"CHAIN: Enhancing Generalization in Data-Efficient GANs via lipsCHitz continuity constrAIned Normalization","created":"2024-03-31","cited_by_count":2,"area":null},{"id":"2407.17834","title":"Towards the Spectral bias Alleviation by Normalizations in Coordinate Networks","created":"2024-07-25","cited_by_count":2,"area":null},{"id":"2506.12903","title":"Variational Learning Finds Flatter Solutions at the Edge of Stability","created":"2025-06-15","cited_by_count":2,"area":null},{"id":"2406.06796","title":"FlexLoc: Conditional Neural Networks for Zero-Shot Sensor Perspective Invariance in Object Localization with Distributed Multimodal Sensors","created":"2024-06-10","cited_by_count":1,"area":null},{"id":"2410.16476","title":"In Search of the Successful Interpolation: On the Role of Sharpness in CLIP Generalization","created":"2024-10-21","cited_by_count":1,"area":null},{"id":"2501.11584","title":"GCSAM: Gradient Centralized Sharpness Aware Minimization","created":"2025-01-20","cited_by_count":1,"area":null},{"id":"2502.04889","title":"Any-stepsize Gradient Descent for Separable Data under Fenchel-Young Losses","created":"2025-02-07","cited_by_count":1,"area":null},{"id":"2510.07758","title":"R\\'enyi Sharpness: A Novel Sharpness that Strongly Correlates with Generalization","created":"2025-10-09","cited_by_count":1,"area":null},{"id":"2602.05065","title":"Does SGD Seek Flatness or Sharpness? An Exactly Solvable Model","created":"2026-02-04","cited_by_count":1,"area":null},{"id":"2604.10202","title":"Wolkowicz-Styan Upper Bound on the Hessian Eigenspectrum for Cross-Entropy Loss in Nonlinear Smooth Neural Networks","created":"2026-04-11","cited_by_count":1,"area":null},{"id":"2605.08894","title":"Fitting Is Not Enough: Smoothness in Extremely Quantized LLMs","created":"2026-05-09","cited_by_count":1,"area":null},{"id":"2605.16622","title":"Does Weight Decay Enhance Training Stability?","created":"2026-05-15","cited_by_count":1,"area":null},{"id":"2605.24420","title":"Batch Normalization Amplifies Memorization and Privacy Risks","created":"2026-05-23","cited_by_count":1,"area":null},{"id":"2606.19105","title":"Smoothness-Based Derandomization of PAC-Bayes Bounds","created":"2026-06-17","cited_by_count":1,"area":null},{"id":"2607.21005","title":"Weight-norm Criticality: A Mechanism for Loss Spikes Induced by the Normalization and Weight Decay","created":"2026-07-23","cited_by_count":1,"area":null},{"id":"2608.18415","title":"The Road Taken: The Role of Optimizers at the Edge of Stability","created":"2026-08-19","cited_by_count":1,"area":null},{"id":"2412.02843","title":"Batch Normalization Decomposed","created":"2024-12-03","cited_by_count":0,"area":null},{"id":"2505.13142","title":"Parallel Layer Normalization for Universal Approximation","created":"2025-05-19","cited_by_count":0,"area":null},{"id":"2511.00958","title":"The Hidden Power of Normalization Layers in Neural Networks: Exponential Capacity Control","created":"2025-11-02","cited_by_count":0,"area":null},{"id":"2601.10251","title":"X-SAM: Boosting Sharpness-Aware Minimization with Dominant-Eigenvector Gradient Correction","created":"2026-01-15","cited_by_count":0,"area":null},{"id":"2606.04212","title":"Edge of Stability Selectively Shapes Learning Across the Data Distribution","created":"2026-06-02","cited_by_count":0,"area":null},{"id":"2606.28662","title":"Closed-Form Steepest Descent Direction toward Flat Minima: Reducing Upper Bounds on the Loss Hessian Eigenspectrum in Neural Networks","created":"2026-06-27","cited_by_count":0,"area":null},{"id":"2608.24173","title":"SandwichQuant: Which Parameters Matter Before and After Quantization?","created":"2026-08-25","cited_by_count":0,"area":null},{"id":"2609.09116","title":"When Does Scale-Invariant Optimization Become Unstable? An Exact Schedule Law with Weight Decay","created":"2026-09-08","cited_by_count":0,"area":null},{"id":"2609.32290","title":"A Journey to the Edge of Stability","created":"2026-09-26","cited_by_count":0,"area":null}],"next_cursor":null}