{"total":54,"rows":[{"id":"2206.15144","title":"Neural Networks can Learn Representations with Gradient Descent","created":"2022-06-30","cited_by_count":161,"area":null},{"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":"2305.16380","title":"Scan and Snap: Understanding Training Dynamics and Token Composition in 1-layer Transformer","created":"2023-05-25","cited_by_count":102,"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":"2202.06526","title":"Benign Overfitting in Two-layer Convolutional Neural Networks","created":"2022-02-14","cited_by_count":91,"area":null},{"id":"2305.10633","title":"Smoothing the Landscape Boosts the Signal for SGD: Optimal Sample Complexity for Learning Single Index Models","created":"2023-05-18","cited_by_count":61,"area":null},{"id":"2310.00535","title":"JoMA: Demystifying Multilayer Transformers via JOint Dynamics of MLP and Attention","created":"2023-10-01","cited_by_count":52,"area":null},{"id":"2103.01210","title":"Quantifying the Benefit of Using Differentiable Learning over Tangent Kernels","created":"2021-03-01","cited_by_count":41,"area":null},{"id":"2205.06226","title":"The Mechanism of Prediction Head in Non-contrastive Self-supervised Learning","created":"2022-05-12","cited_by_count":38,"area":null},{"id":"2309.03843","title":"Gradient-Based Feature Learning under Structured Data","created":"2023-09-07","cited_by_count":32,"area":null},{"id":"2302.06512","title":"Near-Optimal Cryptographic Hardness of Agnostically Learning Halfspaces and ReLU Regression under Gaussian Marginals","created":"2023-02-13","cited_by_count":31,"area":null},{"id":"2302.10034","title":"Over-Parameterization Exponentially Slows Down Gradient Descent for Learning a Single Neuron","created":"2023-02-20","cited_by_count":25,"area":null},{"id":"2402.04084","title":"Provably learning a multi-head attention layer","created":"2024-02-06","cited_by_count":21,"area":null},{"id":"2106.10744","title":"On the Cryptographic Hardness of Learning Single Periodic Neurons","created":"2021-06-20","cited_by_count":20,"area":null},{"id":"2206.08918","title":"Learning a Single Neuron with Adversarial Label Noise via Gradient Descent","created":"2022-06-17","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":"2305.06986","title":"Provable Guarantees for Nonlinear Feature Learning in Three-Layer Neural Networks","created":"2023-05-11","cited_by_count":19,"area":null},{"id":"2106.01101","title":"Learning a Single Neuron with Bias Using Gradient Descent","created":"2021-06-02","cited_by_count":17,"area":null},{"id":"2307.15804","title":"On Single Index Models beyond Gaussian Data","created":"2023-07-28","cited_by_count":17,"area":null},{"id":"2402.19262","title":"Masks, Signs, And Learning Rate Rewinding","created":"2024-02-29","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":"2202.08064","title":"Learning a Single Neuron for Non-monotonic Activation Functions","created":"2022-02-16","cited_by_count":13,"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":"2306.07892","title":"Robustly Learning a Single Neuron via Sharpness","created":"2023-06-13","cited_by_count":12,"area":null},{"id":"2210.05956","title":"Towards Theoretically Inspired Neural Initialization Optimization","created":"2022-10-12","cited_by_count":11,"area":null},{"id":"2109.04623","title":"ReLU Regression with Massart Noise","created":"2021-09-10","cited_by_count":10,"area":null},{"id":"2101.07150","title":"Stable Recovery of Entangled Weights: Towards Robust Identification of Deep Neural Networks from Minimal Samples","created":"2021-01-18","cited_by_count":8,"area":null},{"id":"2303.02255","title":"Finite-Sample Analysis of Learning High-Dimensional Single ReLU Neuron","created":"2023-03-03","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":"2307.12496","title":"A faster and simpler algorithm for learning shallow networks","created":"2023-07-24","cited_by_count":7,"area":null},{"id":"2210.09949","title":"SQ Lower Bounds for Learning Single Neurons with Massart Noise","created":"2022-10-18","cited_by_count":5,"area":null},{"id":"2211.04589","title":"Finite Sample Identification of Wide Shallow Neural Networks with Biases","created":"2022-11-08","cited_by_count":5,"area":null},{"id":"2411.14349","title":"Agnostic Learning of Arbitrary ReLU Activation under Gaussian Marginals","created":"2024-11-21","cited_by_count":5,"area":null},{"id":"2406.05822","title":"Symmetric Matrix Completion with ReLU Sampling","created":"2024-06-09","cited_by_count":4,"area":null},{"id":"2411.05708","title":"Sample and Computationally Efficient Robust Learning of Gaussian Single-Index Models","created":"2024-11-08","cited_by_count":4,"area":null},{"id":"2111.06027","title":"Theoretical Exploration of Flexible Transmitter Model","created":"2021-11-11","cited_by_count":3,"area":null},{"id":"2209.15265","title":"Overparameterized ReLU Neural Networks Learn the Simplest Models: Neural Isometry and Exact Recovery","created":"2022-09-30","cited_by_count":3,"area":null},{"id":"2308.08070","title":"Max-affine regression via first-order methods","created":"2023-08-15","cited_by_count":3,"area":null},{"id":"2310.03956","title":"Gradient Descent Provably Solves Nonlinear Tomographic Reconstruction","created":"2023-10-06","cited_by_count":3,"area":null},{"id":"2411.06697","title":"Learning a Single Neuron Robustly to Distributional Shifts and Adversarial Label Noise","created":"2024-11-11","cited_by_count":2,"area":null},{"id":"2309.11657","title":"Distribution-Independent Regression for Generalized Linear Models with Oblivious Corruptions","created":"2023-09-20","cited_by_count":1,"area":null},{"id":"2411.17567","title":"Improving the Convergence Rates of Forward Gradient Descent with Repeated Sampling","created":"2024-11-26","cited_by_count":1,"area":null},{"id":"2505.21336","title":"Joint Learning in the Gaussian Single Index Model","created":"2025-05-27","cited_by_count":1,"area":null},{"id":"2602.17876","title":"Interactive Learning of Single-Index Models via Stochastic Gradient Descent","created":"2026-02-19","cited_by_count":1,"area":null},{"id":"2606.04476","title":"When Both Layers Learn: Training Dynamics of Representing Linear Models via ReLU Networks","created":"2026-06-03","cited_by_count":1,"area":null},{"id":"2201.07934","title":"Complexity from Adaptive-Symmetries Breaking: Global Minima in the Statistical Mechanics of Deep Neural Networks","created":"2022-01-03","cited_by_count":0,"area":null},{"id":"2206.03254","title":"Demystifying the Global Convergence Puzzle of Learning Over-parameterized ReLU Nets in Very High Dimensions","created":"2022-06-05","cited_by_count":0,"area":null},{"id":"2404.07864","title":"Inferring Change Points in High-Dimensional Regression via Approximate Message Passing","created":"2024-04-11","cited_by_count":0,"area":null},{"id":"2410.05022","title":"On subdifferential chain rule of matrix factorization and beyond","created":"2024-10-07","cited_by_count":0,"area":null},{"id":"2504.01875","title":"AYLA: Architecting a loss landscape in shallow neural networks to accelerate feature recovery","created":"2025-04-02","cited_by_count":0,"area":null},{"id":"2510.19382","title":"A Derandomization Framework for Structure Discovery: Applications in Neural Networks and Beyond","created":"2025-10-22","cited_by_count":0,"area":null},{"id":"2601.18115","title":"Robust Learning of a Group DRO Neuron","created":"2026-01-26","cited_by_count":0,"area":null},{"id":"2607.06369","title":"Feature Learning for the High Dimensional Stationary Sch\\\"odinger Equation with Deep Ritz Method","created":"2026-07-07","cited_by_count":0,"area":null},{"id":"2609.34667","title":"Two-Timescale Fine-tuning Provably Learns New Features for Two-Layer ReLU Networks","created":"2026-09-28","cited_by_count":0,"area":null}],"next_cursor":null}