{"total":74,"rows":[{"id":"2105.15134","title":"Toward Understanding the Feature Learning Process of Self-supervised Contrastive Learning","created":"2021-05-31","cited_by_count":119,"area":null},{"id":"2203.09081","title":"Inducing Neural Collapse in Imbalanced Learning: Do We Really Need a Learnable Classifier at the End of Deep Neural Network?","created":"2022-03-17","cited_by_count":100,"area":null},{"id":"2210.15651","title":"Learning Single-Index Models with Shallow Neural Networks","created":"2022-10-27","cited_by_count":92,"area":null},{"id":"2106.15013","title":"Small random initialization is akin to spectral learning: Optimization and generalization guarantees for overparameterized low-rank matrix reconstruction","created":"2021-06-28","cited_by_count":78,"area":null},{"id":"2106.14289","title":"Global Convergence of Gradient Descent for Asymmetric Low-Rank Matrix Factorization","created":"2021-06-27","cited_by_count":45,"area":null},{"id":"2103.05134","title":"Constrained Learning with Non-Convex Losses","created":"2021-03-08","cited_by_count":42,"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":"2110.15767","title":"Adversarial Robustness with Semi-Infinite Constrained Learning","created":"2021-10-29","cited_by_count":39,"area":null},{"id":"2309.15111","title":"SGD Finds then Tunes Features in Two-Layer Neural Networks with near-Optimal Sample Complexity: A Case Study in the XOR problem","created":"2023-09-26","cited_by_count":39,"area":null},{"id":"2202.05258","title":"Hardness of Noise-Free Learning for Two-Hidden-Layer Neural Networks","created":"2022-02-10","cited_by_count":28,"area":null},{"id":"2110.05518","title":"Global Optimality Beyond Two Layers: Training Deep ReLU Networks via Convex Programs","created":"2021-10-11","cited_by_count":25,"area":null},{"id":"2105.14417","title":"Overparameterization of deep ResNet: zero loss and mean-field analysis","created":"2021-05-30","cited_by_count":24,"area":null},{"id":"2112.12982","title":"Parameter identifiability of a deep feedforward ReLU neural network","created":"2021-12-24","cited_by_count":24,"area":null},{"id":"2402.04084","title":"Provably learning a multi-head attention layer","created":"2024-02-06","cited_by_count":21,"area":null},{"id":"2106.06573","title":"Understanding Deflation Process in Over-parametrized Tensor Decomposition","created":"2021-06-11","cited_by_count":20,"area":null},{"id":"2106.10744","title":"On the Cryptographic Hardness of Learning Single Periodic Neurons","created":"2021-06-20","cited_by_count":20,"area":null},{"id":"2306.16361","title":"Beyond NTK with Vanilla Gradient Descent: A Mean-Field Analysis of Neural Networks with Polynomial Width, Samples, and Time","created":"2023-06-28","cited_by_count":20,"area":null},{"id":"2110.08616","title":"GradSign: Model Performance Inference with Theoretical Insights","created":"2021-10-16","cited_by_count":19,"area":null},{"id":"2201.08514","title":"How does unlabeled data improve generalization in self-training? A one-hidden-layer theoretical analysis","created":"2022-01-21","cited_by_count":19,"area":null},{"id":"2310.16173","title":"On the Convergence and Sample Complexity Analysis of Deep Q-Networks with $\\epsilon$-Greedy Exploration","created":"2023-10-24","cited_by_count":17,"area":null},{"id":"2107.10370","title":"Analytic Study of Families of Spurious Minima in Two-Layer ReLU Neural Networks: A Tale of Symmetry II","created":"2021-07-21","cited_by_count":16,"area":null},{"id":"2107.04518","title":"Optimal Gradient-based Algorithms for Non-concave Bandit Optimization","created":"2021-07-09","cited_by_count":15,"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":"2206.12802","title":"Bounding the Width of Neural Networks via Coupled Initialization -- A Worst Case Analysis","created":"2022-06-26","cited_by_count":15,"area":null},{"id":"2306.02426","title":"Resilient Constrained Learning","created":"2023-06-04","cited_by_count":15,"area":null},{"id":"2110.09548","title":"Path Regularization: A Convexity and Sparsity Inducing Regularization for Parallel ReLU Networks","created":"2021-10-18","cited_by_count":14,"area":null},{"id":"2201.06699","title":"AESPA: Accuracy Preserving Low-degree Polynomial Activation for Fast Private Inference","created":"2022-01-18","cited_by_count":14,"area":null},{"id":"2304.10524","title":"Learning Narrow One-Hidden-Layer ReLU Networks","created":"2023-04-20","cited_by_count":14,"area":null},{"id":"2206.03688","title":"Identifying good directions to escape the NTK regime and efficiently learn low-degree plus sparse polynomials","created":"2022-06-08","cited_by_count":13,"area":null},{"id":"2110.02926","title":"On the Global Convergence of Gradient Descent for multi-layer ResNets in the mean-field regime","created":"2021-10-06","cited_by_count":12,"area":null},{"id":"2206.07424","title":"Local Identifiability of Deep ReLU Neural Networks: the Theory","created":"2022-06-15","cited_by_count":12,"area":null},{"id":"2208.02711","title":"Agnostic Learning of General ReLU Activation Using Gradient Descent","created":"2022-08-04","cited_by_count":12,"area":null},{"id":"2111.14069","title":"Escape saddle points by a simple gradient-descent based algorithm","created":"2021-11-28","cited_by_count":11,"area":null},{"id":"2210.05956","title":"Towards Theoretically Inspired Neural Initialization Optimization","created":"2022-10-12","cited_by_count":11,"area":null},{"id":"2302.07426","title":"Computational Complexity of Learning Neural Networks: Smoothness and Degeneracy","created":"2023-02-15","cited_by_count":10,"area":null},{"id":"2107.06466","title":"Going Beyond Linear RL: Sample Efficient Neural Function Approximation","created":"2021-07-14","cited_by_count":9,"area":null},{"id":"2210.06088","title":"Annihilation of Spurious Minima in Two-Layer ReLU Networks","created":"2022-10-12","cited_by_count":9,"area":null},{"id":"2403.11844","title":"Near-Optimal Solutions of Constrained Learning Problems","created":"2024-03-18","cited_by_count":9,"area":null},{"id":"2502.09525","title":"Robust Learning of Multi-index Models via Iterative Subspace Approximation","created":"2025-02-13","cited_by_count":9,"area":null},{"id":"2103.13462","title":"Why Do Local Methods Solve Nonconvex Problems?","created":"2021-03-24","cited_by_count":8,"area":null},{"id":"2111.03135","title":"Scaffolding Sets","created":"2021-11-04","cited_by_count":8,"area":null},{"id":"2301.12540","title":"Implicit Regularization for Group Sparsity","created":"2023-01-29","cited_by_count":8,"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":"2102.13233","title":"Spurious Local Minima Are Common for Deep Neural Networks with Piecewise Linear Activations","created":"2021-02-25","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":"2109.14142","title":"On the Provable Generalization of Recurrent Neural Networks","created":"2021-09-29","cited_by_count":6,"area":null},{"id":"2111.04727","title":"Efficiently Learning Any One Hidden Layer ReLU Network From Queries","created":"2021-11-08","cited_by_count":6,"area":null},{"id":"2203.00246","title":"An Information-Theoretic Framework for Supervised Learning","created":"2022-03-01","cited_by_count":6,"area":null},{"id":"2210.01496","title":"Zeroth-Order Negative Curvature Finding: Escaping Saddle Points without Gradients","created":"2022-10-04","cited_by_count":6,"area":null},{"id":"2403.07310","title":"How does promoting the minority fraction affect generalization? A theoretical study of the one-hidden-layer neural network on group imbalance","created":"2024-03-12","cited_by_count":6,"area":null},{"id":"2411.15669","title":"Implicit High-Order Moment Tensor Estimation and Learning Latent Variable Models","created":"2024-11-23","cited_by_count":6,"area":null},{"id":"2109.10935","title":"Robust Generalization of Quadratic Neural Networks via Function Identification","created":"2021-09-22","cited_by_count":5,"area":null},{"id":"2208.10025","title":"Simple and Optimal Stochastic Gradient Methods for Nonsmooth Nonconvex Optimization","created":"2022-08-22","cited_by_count":5,"area":null},{"id":"2106.12068","title":"The Rate of Convergence of Variation-Constrained Deep Neural Networks","created":"2021-06-22","cited_by_count":4,"area":null},{"id":"2305.04267","title":"Provable Identifiability of Two-Layer ReLU Neural Networks via LASSO Regularization","created":"2023-05-07","cited_by_count":4,"area":null},{"id":"2307.12840","title":"Efficiently Learning One-Hidden-Layer ReLU Networks via Schur Polynomials","created":"2023-07-24","cited_by_count":4,"area":null},{"id":"2309.17357","title":"Module-wise Training of Neural Networks via the Minimizing Movement Scheme","created":"2023-09-29","cited_by_count":4,"area":null},{"id":"2406.01766","title":"How Does Gradient Descent Learn Features -- A Local Analysis for Regularized Two-Layer Neural Networks","created":"2024-06-03","cited_by_count":4,"area":null},{"id":"2407.07670","title":"Generalization Analysis of Online Stochastic Gradient Descent for Overparameterized Two-Layer Neural Networks","created":"2024-07-10","cited_by_count":4,"area":null},{"id":"2502.16021","title":"Learning Neural Networks with Distribution Shift: Efficiently Certifiable Guarantees","created":"2025-02-22","cited_by_count":4,"area":null},{"id":"2209.08627","title":"Is Stochastic Gradient Descent Near Optimal?","created":"2022-09-18","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":"2311.10972","title":"Polynomial-Time Solutions for ReLU Network Training: A Complexity Classification via Max-Cut and Zonotopes","created":"2023-11-18","cited_by_count":2,"area":null},{"id":"2312.16819","title":"Hidden Minima in Two-Layer ReLU Networks","created":"2023-12-28","cited_by_count":2,"area":null},{"id":"2508.18408","title":"Low-Rank Tensor Decompositions for the Theory of Neural Networks","created":"2025-08-25","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":"2607.03347","title":"The Multiscale Single-Index Model: A Stylized Model for Hierarchical Feature Learning","created":"2026-07-03","cited_by_count":2,"area":null},{"id":"2203.16455","title":"Explicitising The Implicit Intrepretability of Deep Neural Networks Via Duality","created":"2022-03-01","cited_by_count":1,"area":null},{"id":"2309.15096","title":"Fixing the NTK: From Neural Network Linearizations to Exact Convex Programs","created":"2023-09-26","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":"2410.03477","title":"On the Hardness of Learning One Hidden Layer Neural Networks","created":"2024-10-04","cited_by_count":1,"area":null},{"id":"2103.01887","title":"Self-Regularity of Non-Negative Output Weights for Overparameterized Two-Layer Neural Networks","created":"2021-03-02","cited_by_count":0,"area":null},{"id":"2411.12854","title":"A new Input Convex Neural Network with application to options pricing","created":"2024-11-19","cited_by_count":0,"area":null},{"id":"2609.10879","title":"Learning Orthogonal Multi-Index Models Beyond Small Initialization: Incremental Learning, Competitive Dynamics and Symmetry","created":"2026-09-09","cited_by_count":0,"area":null}],"next_cursor":null}