{"total":38,"rows":[{"id":"2306.11695","title":"A Simple and Effective Pruning Approach for Large Language Models","created":"2023-06-20","cited_by_count":800,"area":null},{"id":"2107.13034","title":"Dataset Distillation with Infinitely Wide Convolutional Networks","created":"2021-07-27","cited_by_count":218,"area":null},{"id":"2210.01117","title":"Omnigrok: Grokking Beyond Algorithmic Data","created":"2022-10-03","cited_by_count":146,"area":null},{"id":"2310.06110","title":"Grokking as the Transition from Lazy to Rich Training Dynamics","created":"2023-10-09","cited_by_count":108,"area":null},{"id":"2205.09653","title":"Self-Consistent Dynamical Field Theory of Kernel Evolution in Wide Neural Networks","created":"2022-05-19","cited_by_count":105,"area":null},{"id":"2206.07085","title":"Understanding the Generalization Benefit of Normalization Layers: Sharpness Reduction","created":"2022-06-14","cited_by_count":86,"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":"2310.04415","title":"Why Do We Need Weight Decay in Modern Deep Learning?","created":"2023-10-06","cited_by_count":72,"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":"2306.03534","title":"Continual Learning in Linear Classification on Separable Data","created":"2023-06-06","cited_by_count":34,"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":"2509.21519","title":"Provable Scaling Laws of Feature Emergence from Learning Dynamics of Grokking","created":"2025-09-25","cited_by_count":15,"area":null},{"id":"2410.03249","title":"How Much Can We Forget about Data Contamination?","created":"2024-10-04","cited_by_count":14,"area":null},{"id":"2502.07998","title":"Adaptive kernel predictors from feature-learning infinite limits of neural networks","created":"2025-02-11","cited_by_count":13,"area":null},{"id":"2306.13339","title":"TrustGuard: GNN-based Robust and Explainable Trust Evaluation with Dynamicity Support","created":"2023-06-23","cited_by_count":12,"area":null},{"id":"2103.12682","title":"How to decay your learning rate","created":"2021-03-23","cited_by_count":11,"area":null},{"id":"2206.01378","title":"Regularization-wise double descent: Why it occurs and how to eliminate it","created":"2022-06-03","cited_by_count":9,"area":null},{"id":"2111.12143","title":"Critical Initialization of Wide and Deep Neural Networks through Partial Jacobians: General Theory and Applications","created":"2021-11-23","cited_by_count":8,"area":null},{"id":"2202.08978","title":"Cyclical Focal Loss","created":"2022-02-16","cited_by_count":8,"area":null},{"id":"2504.17160","title":"OUI Need to Talk About Weight Decay: A New Perspective on Overfitting Detection","created":"2025-04-24","cited_by_count":7,"area":null},{"id":"2202.08835","title":"General Cyclical Training of Neural Networks","created":"2022-02-17","cited_by_count":5,"area":null},{"id":"2311.09058","title":"Improving Deep Learning Optimization through Constrained Parameter Regularization","created":"2023-11-15","cited_by_count":5,"area":null},{"id":"2502.01556","title":"A Gaussian Process View on Observation Noise and Initialization in Wide Neural Networks","created":"2025-02-03","cited_by_count":5,"area":null},{"id":"2410.11985","title":"The Fair Language Model Paradox","created":"2024-10-15","cited_by_count":4,"area":null},{"id":"2509.07027","title":"Moment- and Power-Spectrum-Based Gaussianity Regularization for Text-to-Image Models","created":"2025-09-07","cited_by_count":3,"area":null},{"id":"2510.05573","title":"On the Theory of Continual Learning with Gradient Descent for Neural Networks","created":"2025-10-07","cited_by_count":3,"area":null},{"id":"2502.01739","title":"Grokking vs. Learning: Same Features, Different Encodings","created":"2025-02-03","cited_by_count":2,"area":null},{"id":"2503.16316","title":"On the Cone Effect in the Learning Dynamics","created":"2025-03-20","cited_by_count":2,"area":null},{"id":"2311.03938","title":"Analysis of NaN Divergence in Training Monocular Depth Estimation Model","created":"2023-11-07","cited_by_count":0,"area":null},{"id":"2406.14068","title":"Classifying Dry Eye Disease Patients from Healthy Controls Using Machine Learning and Metabolomics Data","created":"2024-06-20","cited_by_count":0,"area":null},{"id":"2512.24445","title":"Adaptive Learning Guided by Bias-Noise-Alignment Diagnostics","created":"2025-12-30","cited_by_count":0,"area":null},{"id":"2602.12613","title":"Coden: Efficient Temporal Graph Neural Networks for Continuous Prediction","created":"2026-02-13","cited_by_count":0,"area":null},{"id":"2603.10397","title":"On the Learning Dynamics of Two-layer Linear Networks with Label Noise SGD","created":"2026-03-11","cited_by_count":0,"area":null},{"id":"2604.05781","title":"RHVI-FDD: A Hierarchical Decoupling Framework for Low-Light Image Enhancement","created":"2026-04-07","cited_by_count":0,"area":null},{"id":"2605.17606","title":"The Neural Tangent Kernel for Classification","created":"2026-05-17","cited_by_count":0,"area":null},{"id":"2605.28679","title":"Optimal ridge regularization revisited","created":"2026-05-27","cited_by_count":0,"area":null},{"id":"2610.00620","title":"Misalignment of Low-Loss Regions Causes Grokking","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2610.04533","title":"Weight Decay and Neuron Condensation: A Three-Stage Analysis of Two-Layer ReLU Networks","created":"2026-10-03","cited_by_count":0,"area":null}],"next_cursor":null}