{"total":54,"rows":[{"id":"2205.09739","title":"Diverse Weight Averaging for Out-of-Distribution Generalization","created":"2022-05-19","cited_by_count":148,"area":null},{"id":"2110.06914","title":"What Happens after SGD Reaches Zero Loss? --A Mathematical Framework","created":"2021-10-13","cited_by_count":107,"area":null},{"id":"2210.09221","title":"Vision Transformers provably learn spatial structure","created":"2022-10-13","cited_by_count":93,"area":null},{"id":"2101.09612","title":"On the Proof of Global Convergence of Gradient Descent for Deep ReLU Networks with Linear Widths","created":"2021-01-24","cited_by_count":44,"area":null},{"id":"2303.15725","title":"Solving Regularized Exp, Cosh and Sinh Regression Problems","created":"2023-03-28","cited_by_count":44,"area":null},{"id":"2307.11353","title":"What can a Single Attention Layer Learn? A Study Through the Random Features Lens","created":"2023-07-21","cited_by_count":40,"area":null},{"id":"2207.03584","title":"Generalization Guarantee of Training Graph Convolutional Networks with Graph Topology Sampling","created":"2022-07-07","cited_by_count":23,"area":null},{"id":"2302.06210","title":"Precise Asymptotic Analysis of Deep Random Feature Models","created":"2023-02-13","cited_by_count":22,"area":null},{"id":"2205.09072","title":"On the Effective Number of Linear Regions in Shallow Univariate ReLU Networks: Convergence Guarantees and Implicit Bias","created":"2022-05-18","cited_by_count":21,"area":null},{"id":"2402.04084","title":"Provably learning a multi-head attention layer","created":"2024-02-06","cited_by_count":21,"area":null},{"id":"2211.16980","title":"Infinite-width limit of deep linear neural networks","created":"2022-11-29","cited_by_count":20,"area":null},{"id":"2201.09910","title":"Learning Neural Contextual Bandits Through Perturbed Rewards","created":"2022-01-24","cited_by_count":17,"area":null},{"id":"2107.10209","title":"Efficient Algorithms for Learning Depth-2 Neural Networks with General ReLU Activations","created":"2021-07-21","cited_by_count":15,"area":null},{"id":"2304.10524","title":"Learning Narrow One-Hidden-Layer ReLU Networks","created":"2023-04-20","cited_by_count":14,"area":null},{"id":"2101.06309","title":"Fundamental Tradeoffs in Distributionally Adversarial Training","created":"2021-01-15","cited_by_count":12,"area":null},{"id":"2101.07833","title":"Implicit Bias of Linear RNNs","created":"2021-01-19","cited_by_count":11,"area":null},{"id":"2205.07331","title":"Sobolev Acceleration and Statistical Optimality for Learning Elliptic Equations via Gradient Descent","created":"2022-05-15","cited_by_count":11,"area":null},{"id":"2305.09779","title":"A Scalable Walsh-Hadamard Regularizer to Overcome the Low-degree Spectral Bias of Neural Networks","created":"2023-05-16","cited_by_count":10,"area":null},{"id":"2305.05765","title":"On the average-case complexity of learning output distributions of quantum circuits","created":"2023-05-09","cited_by_count":9,"area":null},{"id":"2406.11129","title":"Neural Lineage","created":"2024-06-17","cited_by_count":9,"area":null},{"id":"2309.07452","title":"Is Solving Graph Neural Tangent Kernel Equivalent to Training Graph Neural Network?","created":"2023-09-14","cited_by_count":8,"area":null},{"id":"2410.06300","title":"SHAP values via sparse Fourier representation","created":"2024-10-08","cited_by_count":8,"area":null},{"id":"2103.13598","title":"Recent Advances in Large Margin Learning","created":"2021-03-25","cited_by_count":7,"area":null},{"id":"2108.04964","title":"A spectral-based analysis of the separation between two-layer neural networks and linear methods","created":"2021-08-10","cited_by_count":7,"area":null},{"id":"2307.12496","title":"A faster and simpler algorithm for learning shallow networks","created":"2023-07-24","cited_by_count":7,"area":null},{"id":"2403.12486","title":"NTK-Guided Few-Shot Class Incremental Learning","created":"2024-03-19","cited_by_count":7,"area":null},{"id":"2207.04612","title":"Synergy and Symmetry in Deep Learning: Interactions between the Data, Model, and Inference Algorithm","created":"2022-07-11","cited_by_count":6,"area":null},{"id":"2102.07238","title":"Double-descent curves in neural networks: a new perspective using Gaussian processes","created":"2021-02-14","cited_by_count":5,"area":null},{"id":"2206.02139","title":"Early Stage Convergence and Global Convergence of Training Mildly Parameterized Neural Networks","created":"2022-06-05","cited_by_count":5,"area":null},{"id":"2305.08001","title":"Structured and Fast Optimization: The Kronecker SGD Algorithm","created":"2023-05-13","cited_by_count":5,"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":"2111.14039","title":"Generalization Performance of Empirical Risk Minimization on Over-parameterized Deep ReLU Nets","created":"2021-11-28","cited_by_count":4,"area":null},{"id":"2206.01332","title":"Optimal Activation Functions for the Random Features Regression Model","created":"2022-05-31","cited_by_count":4,"area":null},{"id":"2302.03669","title":"Deep Reinforcement Learning for Traffic Light Control in Intelligent Transportation Systems","created":"2023-02-04","cited_by_count":3,"area":null},{"id":"2404.14875","title":"Regularized Gauss-Newton for Optimizing Overparameterized Neural Networks","created":"2024-04-23","cited_by_count":3,"area":null},{"id":"2510.14331","title":"LLM Priors for ERM over Programs","created":"2025-10-16","cited_by_count":3,"area":null},{"id":"2101.02333","title":"Infinitely Wide Tensor Networks as Gaussian Process","created":"2021-01-07","cited_by_count":2,"area":null},{"id":"2305.16508","title":"Most Neural Networks Are Almost Learnable","created":"2023-05-25","cited_by_count":2,"area":null},{"id":"2601.00455","title":"Deep Networks Learn Deep Hierarchical Models","created":"2026-01-01","cited_by_count":2,"area":null},{"id":"2201.06658","title":"Learning Neural Ranking Models Online from Implicit User Feedback","created":"2022-01-17","cited_by_count":1,"area":null},{"id":"2302.00205","title":"Gradient Descent in Neural Networks as Sequential Learning in RKBS","created":"2023-02-01","cited_by_count":1,"area":null},{"id":"2306.02833","title":"The $L^\\infty$ Learnability of Reproducing Kernel Hilbert Spaces","created":"2023-06-05","cited_by_count":1,"area":null},{"id":"2311.15404","title":"Applying statistical learning theory to deep learning","created":"2023-11-26","cited_by_count":1,"area":null},{"id":"2401.07606","title":"RedEx: Beyond Fixed Representation Methods via Convex Optimization","created":"2024-01-15","cited_by_count":1,"area":null},{"id":"2503.17865","title":"Understanding Inverse Reinforcement Learning under Overparameterization: Non-Asymptotic Analysis and Global Optimality","created":"2025-03-22","cited_by_count":1,"area":"offlinerl"},{"id":"2506.21894","title":"Thompson Sampling in Function Spaces via Neural Operators","created":"2025-06-27","cited_by_count":1,"area":null},{"id":"2103.16355","title":"Nonlinear Weighted Directed Acyclic Graph and A Priori Estimates for Neural Networks","created":"2021-03-30","cited_by_count":0,"area":null},{"id":"2301.11414","title":"A Simple Algorithm For Scaling Up Kernel Methods","created":"2023-01-26","cited_by_count":0,"area":null},{"id":"2401.04013","title":"Weak Correlations as the Underlying Principle for Linearization of Gradient-Based Learning Systems","created":"2024-01-08","cited_by_count":0,"area":null},{"id":"2405.15254","title":"Novel Kernel Models and Exact Representor Theory for Neural Networks Beyond the Over-Parameterized Regime","created":"2024-05-24","cited_by_count":0,"area":null},{"id":"2406.09194","title":"Benign overfitting in Fixed Dimension via Physics-Informed Learning with Smooth Inductive Bias","created":"2024-06-13","cited_by_count":0,"area":null},{"id":"2505.10423","title":"The Power of Random Features and the Limits of Distribution-Free Gradient Descent","created":"2025-05-15","cited_by_count":0,"area":null},{"id":"2505.11347","title":"Training NTK to Generalize with KARE","created":"2025-05-16","cited_by_count":0,"area":null},{"id":"2603.12276","title":"No More DeLuLu: Physics-Inspired Kernel Networks for Geometrically-Grounded Neural Computation","created":"2026-02-22","cited_by_count":0,"area":null}],"next_cursor":null}