{"total":61,"rows":[{"id":"2102.06810","title":"Understanding self-supervised Learning Dynamics without Contrastive Pairs","created":"2021-02-12","cited_by_count":256,"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":"2209.14863","title":"Neural Networks Efficiently Learn Low-Dimensional Representations with SGD","created":"2022-09-29","cited_by_count":63,"area":null},{"id":"2112.15383","title":"Separation of Scales and a Thermodynamic Description of Feature Learning in Some CNNs","created":"2021-12-31","cited_by_count":53,"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":"2103.05134","title":"Constrained Learning with Non-Convex Losses","created":"2021-03-08","cited_by_count":42,"area":null},{"id":"2110.15767","title":"Adversarial Robustness with Semi-Infinite Constrained Learning","created":"2021-10-29","cited_by_count":39,"area":null},{"id":"2201.08025","title":"Low-Pass Filtering SGD for Recovering Flat Optima in the Deep Learning Optimization Landscape","created":"2022-01-20","cited_by_count":39,"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":"2306.13575","title":"Scaling MLPs: A Tale of Inductive Bias","created":"2023-06-23","cited_by_count":37,"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":"2111.01875","title":"Subquadratic Overparameterization for Shallow Neural Networks","created":"2021-11-02","cited_by_count":26,"area":null},{"id":"2209.03525","title":"Implicit Full Waveform Inversion with Deep Neural Representation","created":"2022-09-08","cited_by_count":26,"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":"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":"2101.08303","title":"From Local Pseudorandom Generators to Hardness of Learning","created":"2021-01-20","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":"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":"2101.02533","title":"Towards Understanding Learning in Neural Networks with Linear Teachers","created":"2021-01-07","cited_by_count":19,"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":"2106.01101","title":"Learning a Single Neuron with Bias Using Gradient Descent","created":"2021-06-02","cited_by_count":17,"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":"2201.01965","title":"Efficient Global Optimization of Two-Layer ReLU Networks: Quadratic-Time Algorithms and Adversarial Training","created":"2022-01-06","cited_by_count":15,"area":null},{"id":"2204.01368","title":"Training Fully Connected Neural Networks is $\\exists\\mathbb{R}$-Complete","created":"2022-04-04","cited_by_count":15,"area":null},{"id":"2306.02426","title":"Resilient Constrained Learning","created":"2023-06-04","cited_by_count":15,"area":null},{"id":"2110.05667","title":"Why Lottery Ticket Wins? A Theoretical Perspective of Sample Complexity on Pruned Neural Networks","created":"2021-10-12","cited_by_count":14,"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":"2401.01869","title":"On the hardness of learning under symmetries","created":"2024-01-03","cited_by_count":13,"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":"2210.05956","title":"Towards Theoretically Inspired Neural Initialization Optimization","created":"2022-10-12","cited_by_count":11,"area":null},{"id":"2402.03625","title":"Convex Relaxations of ReLU Neural Networks Approximate Global Optima in Polynomial Time","created":"2024-02-06","cited_by_count":11,"area":null},{"id":"2509.09033","title":"Generative quantum advantage for classical and quantum problems","created":"2025-09-10","cited_by_count":11,"area":null},{"id":"2107.10868","title":"Local SGD Optimizes Overparameterized Neural Networks in Polynomial Time","created":"2021-07-22","cited_by_count":10,"area":null},{"id":"2205.14818","title":"Excess Risk of Two-Layer ReLU Neural Networks in Teacher-Student Settings and its Superiority to Kernel Methods","created":"2022-05-30","cited_by_count":10,"area":"distill"},{"id":"2306.17378","title":"Global Optimality in Bivariate Gradient-based DAG Learning","created":"2023-06-30","cited_by_count":10,"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":"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":"2103.13462","title":"Why Do Local Methods Solve Nonconvex Problems?","created":"2021-03-24","cited_by_count":8,"area":null},{"id":"2209.13394","title":"Magnitude and Angle Dynamics in Training Single ReLU Neurons","created":"2022-09-27","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":"2101.04243","title":"A Convergence Theory Towards Practical Over-parameterized Deep Neural Networks","created":"2021-01-12","cited_by_count":4,"area":null},{"id":"2105.12237","title":"Practical Convex Formulation of Robust One-hidden-layer Neural Network Training","created":"2021-05-25","cited_by_count":4,"area":null},{"id":"2303.11249","title":"What Makes Data Suitable for a Locally Connected Neural Network? A Necessary and Sufficient Condition Based on Quantum Entanglement","created":"2023-03-20","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":"2104.11895","title":"Achieving Small Test Error in Mildly Overparameterized Neural Networks","created":"2021-04-24","cited_by_count":3,"area":null},{"id":"2503.20879","title":"Quantum advantage for learning shallow neural networks with natural data distributions","created":"2025-03-26","cited_by_count":3,"area":null},{"id":"2509.19773","title":"Sobolev acceleration for neural networks","created":"2025-09-24","cited_by_count":3,"area":null},{"id":"2312.16819","title":"Hidden Minima in Two-Layer ReLU Networks","created":"2023-12-28","cited_by_count":2,"area":null},{"id":"2401.03214","title":"Understanding Representation Learnability of Nonlinear Self-Supervised Learning","created":"2024-01-06","cited_by_count":2,"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":"2102.09798","title":"Training Neural Networks is $\\exists\\mathbb R$-complete","created":"2021-02-19","cited_by_count":0,"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":"2104.01730","title":"Training Deep Neural Networks via Branch-and-Bound","created":"2021-04-05","cited_by_count":0,"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":"2307.07726","title":"Towards Optimal Neural Networks: the Role of Sample Splitting in Hyperparameter Selection","created":"2023-07-15","cited_by_count":0,"area":null},{"id":"2407.20870","title":"Mean of Means: A 10-dollar Solution for Human Localization with Calibration-free and Unconstrained Camera Settings","created":"2024-07-30","cited_by_count":0,"area":null}],"next_cursor":null}