{"total":21,"rows":[{"id":"2301.05603","title":"A Comprehensive Survey of Dataset Distillation","created":"2023-01-13","cited_by_count":115,"area":null},{"id":"2301.11300","title":"ZiCo: Zero-shot NAS via Inverse Coefficient of Variation on Gradients","created":"2023-01-26","cited_by_count":58,"area":null},{"id":"2310.11046","title":"Fast Graph Condensation with Structure-based Neural Tangent Kernel","created":"2023-10-17","cited_by_count":36,"area":null},{"id":"2403.03103","title":"Emergent Equivariance in Deep Ensembles","created":"2024-03-05","cited_by_count":18,"area":null},{"id":"2303.15484","title":"Regularize implicit neural representation by itself","created":"2023-03-27","cited_by_count":13,"area":null},{"id":"2309.08044","title":"How many Neurons do we need? A refined Analysis for Shallow Networks trained with Gradient Descent","created":"2023-09-14","cited_by_count":10,"area":null},{"id":"2411.00247","title":"Deep Learning Through A Telescoping Lens: A Simple Model Provides Empirical Insights On Grokking, Gradient Boosting & Beyond","created":"2024-10-31","cited_by_count":9,"area":null},{"id":"2412.17518","title":"Optimal Convergence Rates for Neural Operators","created":"2024-12-23","cited_by_count":8,"area":null},{"id":"2502.00869","title":"A Unified Theory of Sinusoidal Activation Families for Implicit Neural Representations","created":"2025-02-02","cited_by_count":4,"area":null},{"id":"2605.18598","title":"Pointwise Generalization in Deep Neural Networks","created":"2026-05-18","cited_by_count":4,"area":null},{"id":"2310.05105","title":"How Graph Neural Networks Learn: Lessons from Training Dynamics","created":"2023-10-08","cited_by_count":3,"area":null},{"id":"2409.03953","title":"Epistemic Uncertainty and Observation Noise with the Neural Tangent Kernel","created":"2024-09-06","cited_by_count":3,"area":null},{"id":"2510.09103","title":"AdaPM: a Partial Momentum Algorithm for LLM Training","created":"2025-10-10","cited_by_count":3,"area":null},{"id":"2212.01744","title":"Statistical Physics of Deep Neural Networks: Initialization toward Optimal Channels","created":"2022-12-04","cited_by_count":2,"area":null},{"id":"2505.14512","title":"Just One Layer Norm Guarantees Stable Extrapolation","created":"2025-05-20","cited_by_count":2,"area":null},{"id":"2603.22155","title":"RAMPAGE: RAndomized Mid-Point for debiAsed Gradient Extrapolation","created":"2026-03-23","cited_by_count":1,"area":null},{"id":"2412.18756","title":"Towards a Statistical Understanding of Neural Networks: Beyond the Neural Tangent Kernel Theories","created":"2024-12-25","cited_by_count":0,"area":null},{"id":"2506.02406","title":"Random at First, Fast at Last: NTK-Guided Fourier Pre-Processing for Tabular DL","created":"2025-06-03","cited_by_count":0,"area":null},{"id":"2603.04438","title":"CogGen: Cognitive-Load-Inspired Fully Unsupervised Deep Generative Modeling for Compressively Sampled MRI Reconstruction","created":"2026-02-20","cited_by_count":0,"area":null},{"id":"2608.26943","title":"Data-driven Koopman mode approximation: A neural power iteration algorithm","created":"2026-08-27","cited_by_count":0,"area":null},{"id":"2609.33016","title":"Relative Generalization Invariance of LLM Pretraining","created":"2026-09-26","cited_by_count":0,"area":null}],"next_cursor":null}