{"total":19,"rows":[{"id":"2406.09405","title":"Why Warmup the Learning Rate? Underlying Mechanisms and Improvements","created":"2024-06-13","cited_by_count":46,"area":null},{"id":"2306.04815","title":"Catapults in SGD: spikes in the training loss and their impact on generalization through feature learning","created":"2023-06-07","cited_by_count":31,"area":null},{"id":"2402.17457","title":"Super Consistency of Neural Network Landscapes and Learning Rate Transfer","created":"2024-02-27","cited_by_count":23,"area":null},{"id":"2408.08944","title":"Information-Theoretic Progress Measures reveal Grokking is an Emergent Phase Transition","created":"2024-08-16","cited_by_count":17,"area":null},{"id":"2410.04642","title":"The Optimization Landscape of SGD Across the Feature Learning Strength","created":"2024-10-06","cited_by_count":13,"area":null},{"id":"2603.05002","title":"Non-Euclidean Gradient Descent Operates at the Edge of Stability","created":"2026-03-05","cited_by_count":9,"area":null},{"id":"2310.17074","title":"Benign Oscillation of Stochastic Gradient Descent with Large Learning Rates","created":"2023-10-26","cited_by_count":8,"area":null},{"id":"2601.16979","title":"A Scalable Measure of Loss Landscape Curvature for Analyzing the Training Dynamics of LLMs","created":"2026-01-23","cited_by_count":8,"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":"2406.01468","title":"Understanding Token Probability Encoding in Output Embeddings","created":"2024-06-03","cited_by_count":6,"area":null},{"id":"2401.07085","title":"Three Mechanisms of Feature Learning in a Linear Network","created":"2024-01-13","cited_by_count":4,"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":"2407.15200","title":"HyperbolicLR: Epoch insensitive learning rate scheduler","created":"2024-07-21","cited_by_count":3,"area":null},{"id":"2510.02670","title":"Topological Invariance and Breakdown in Learning","created":"2025-10-03","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":"2504.01737","title":"Enlightenment Period Improving DNN Performance","created":"2025-04-02","cited_by_count":0,"area":null},{"id":"2512.21447","title":"An Equivariance Toolbox for Learning Dynamics","created":"2025-12-24","cited_by_count":0,"area":null},{"id":"2607.13631","title":"How the Hessian-Spectrum of Neural Networks Depends on Data","created":"2026-07-15","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}