{"total":33,"rows":[{"id":"2209.15055","title":"Implicit Bias of Large Depth Networks: a Notion of Rank for Nonlinear Functions","created":"2022-09-29","cited_by_count":38,"area":null},{"id":"2506.13018","title":"Symmetry in Neural Network Parameter Spaces","created":"2025-06-16","cited_by_count":36,"area":null},{"id":"2408.11804","title":"Approaching Deep Learning through the Spectral Dynamics of Weights","created":"2024-08-21","cited_by_count":31,"area":null},{"id":"2307.12851","title":"Early Neuron Alignment in Two-layer ReLU Networks with Small Initialization","created":"2023-07-24","cited_by_count":28,"area":null},{"id":"2210.03820","title":"The Asymmetric Maximum Margin Bias of Quasi-Homogeneous Neural Networks","created":"2022-10-07","cited_by_count":25,"area":null},{"id":"2407.11239","title":"From Low Rank Gradient Subspace Stabilization to Low-Rank Weights: Observations, Theories, and Applications","created":"2024-07-15","cited_by_count":25,"area":null},{"id":"2303.07608","title":"On the Implicit Geometry of Cross-Entropy Parameterizations for Label-Imbalanced Data","created":"2023-03-14","cited_by_count":23,"area":null},{"id":"2206.05794","title":"SGD and Weight Decay Secretly Minimize the Rank of Your Neural Network","created":"2022-06-12","cited_by_count":19,"area":null},{"id":"2305.16534","title":"Variation Spaces for Multi-Output Neural Networks: Insights on Multi-Task Learning and Network Compression","created":"2023-05-25","cited_by_count":18,"area":null},{"id":"2305.19008","title":"Bottleneck Structure in Learned Features: Low-Dimension vs Regularity Tradeoff","created":"2023-05-30","cited_by_count":17,"area":null},{"id":"2405.14468","title":"Neural Collapse versus Low-rank Bias: Is Deep Neural Collapse Really Optimal?","created":"2024-05-23","cited_by_count":17,"area":null},{"id":"2512.20607","title":"Saddle-to-Saddle Dynamics Explains A Simplicity Bias Across Neural Network Architectures","created":"2025-12-23","cited_by_count":15,"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":"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":"2401.01869","title":"On the hardness of learning under symmetries","created":"2024-01-03","cited_by_count":13,"area":null},{"id":"2410.23169","title":"The Persistence of Neural Collapse Despite Low-Rank Bias","created":"2024-10-30","cited_by_count":13,"area":null},{"id":"2202.09028","title":"On the Implicit Bias Towards Minimal Depth of Deep Neural Networks","created":"2022-02-18","cited_by_count":12,"area":null},{"id":"2402.03991","title":"Provable Emergence of Deep Neural Collapse and Low-Rank Bias in $L^2$-Regularized Nonlinear Networks","created":"2024-02-06","cited_by_count":11,"area":null},{"id":"2310.07235","title":"Are GATs Out of Balance?","created":"2023-10-11","cited_by_count":10,"area":null},{"id":"2605.18632","title":"Position: Weight Space Should Be a First-Class Generative AI Modality","created":"2026-05-18","cited_by_count":6,"area":null},{"id":"2305.09145","title":"Deep ReLU Networks Have Surprisingly Simple Polytopes","created":"2023-05-16","cited_by_count":5,"area":null},{"id":"2312.02470","title":"Generator Born from Classifier","created":"2023-12-05","cited_by_count":4,"area":null},{"id":"2406.12615","title":"When Are Bias-Free ReLU Networks Effectively Linear Networks?","created":"2024-06-18","cited_by_count":4,"area":null},{"id":"2508.07370","title":"Intrinsic training dynamics of deep neural networks","created":"2025-08-10","cited_by_count":4,"area":null},{"id":"2603.03597","title":"NuMuon: Nuclear-Norm-Constrained Muon for Compressible LLM Training","created":"2026-03-04","cited_by_count":4,"area":null},{"id":"2206.08257","title":"Gradient Descent for Low-Rank Functions","created":"2022-06-16","cited_by_count":3,"area":null},{"id":"2605.18319","title":"The Symmetries of Three-Layer ReLU Networks","created":"2026-05-18","cited_by_count":3,"area":null},{"id":"2410.02176","title":"Towards Better Generalization: Weight Decay Induces Low-rank Bias for Neural Networks","created":"2024-10-03","cited_by_count":2,"area":null},{"id":"2506.12284","title":"GrokAlign: Geometric Characterisation and Acceleration of Grokking","created":"2025-06-14","cited_by_count":2,"area":null},{"id":"2501.16322","title":"Implicit Bias in Matrix Factorization and its Explicit Realization in a New Architecture","created":"2025-01-27","cited_by_count":1,"area":null},{"id":"2502.05668","title":"The late-stage training dynamics of (stochastic) subgradient descent on homogeneous neural networks","created":"2025-02-08","cited_by_count":1,"area":null},{"id":"2606.19878","title":"On the Oracle Complexity of Interpolation-Based Gradient Descent","created":"2026-06-18","cited_by_count":0,"area":null},{"id":"2609.34549","title":"On Parameter Symmetries and Conservation Laws in Gradient Flow","created":"2026-09-28","cited_by_count":0,"area":null}],"next_cursor":null}