{"total":20,"rows":[{"id":"2409.17858","title":"How Feature Learning Can Improve Neural Scaling Laws","created":"2024-09-26","cited_by_count":56,"area":null},{"id":"2405.17580","title":"Mixed Dynamics In Linear Networks: Unifying the Lazy and Active Regimes","created":"2024-05-27","cited_by_count":18,"area":null},{"id":"2509.10167","title":"The Hidden Width of Deep ResNets: Tight Error Bounds and Phase Diagram","created":"2025-09-12","cited_by_count":17,"area":null},{"id":"2402.18724","title":"Learning Associative Memories with Gradient Descent","created":"2024-02-28","cited_by_count":16,"area":null},{"id":"2312.08410","title":"Universal approximation property of Banach space-valued random feature models including random neural networks","created":"2023-12-13","cited_by_count":13,"area":null},{"id":"2406.03260","title":"Feature learning in finite-width Bayesian deep linear networks with multiple outputs and convolutional layers","created":"2024-06-05","cited_by_count":12,"area":null},{"id":"2506.01502","title":"Learning of Population Dynamics: Inverse Optimization Meets JKO Scheme","created":"2025-06-02","cited_by_count":9,"area":null},{"id":"2509.09088","title":"An entropy formula for the Deep Linear Network","created":"2025-09-11","cited_by_count":8,"area":null},{"id":"2510.15262","title":"Robust Layerwise Scaling Rules by Proper Weight Decay Tuning","created":"2025-10-17","cited_by_count":8,"area":null},{"id":"2506.15025","title":"Optimal Embedding Learning Rate in LLMs: The Effect of Vocabulary Size","created":"2025-06-17","cited_by_count":6,"area":null},{"id":"2307.01177","title":"Neural Hilbert Ladders: Multi-Layer Neural Networks in Function Space","created":"2023-07-03","cited_by_count":5,"area":null},{"id":"2411.15267","title":"Proportional infinite-width infinite-depth limit for deep linear neural networks","created":"2024-11-22","cited_by_count":3,"area":null},{"id":"2511.01734","title":"A Proof of Learning Rate Transfer under $\\mu$P","created":"2025-11-03","cited_by_count":3,"area":null},{"id":"2307.04779","title":"Law of Large Numbers for Bayesian two-layer Neural Network trained with Variational Inference","created":"2023-07-10","cited_by_count":1,"area":null},{"id":"2311.14120","title":"Weight fluctuations in (deep) linear neural networks and a derivation of the inverse-variance flatness relation","created":"2023-11-23","cited_by_count":1,"area":null},{"id":"2410.17128","title":"Understanding Transfer Learning via Mean-field Analysis","created":"2024-10-22","cited_by_count":1,"area":null},{"id":"2601.01306","title":"Towards a Principled Muon under $\\mu\\mathsf{P}$: Ensuring Spectral Conditions throughout Training","created":"2026-01-04","cited_by_count":0,"area":null},{"id":"2602.22925","title":"Beyond NNGP: Large Deviations and Feature Learning in Bayesian Neural Networks","created":"2026-02-26","cited_by_count":0,"area":null},{"id":"2605.08352","title":"Convergence Analysis of Newton's Method for Neural Networks in the Overparameterized Limit","created":"2026-05-08","cited_by_count":0,"area":null},{"id":"2608.11479","title":"Convergence Guarantees of Gradient Descent for Neural Networks via Generalized Lipschitz Smoothness","created":"2026-08-11","cited_by_count":0,"area":null}],"next_cursor":null}