{"total":79,"rows":[{"id":"2102.02887","title":"Do We Actually Need Dense Over-Parameterization? In-Time Over-Parameterization in Sparse Training","created":"2021-02-04","cited_by_count":110,"area":null},{"id":"2109.11676","title":"Theory of overparametrization in quantum neural networks","created":"2021-09-23","cited_by_count":100,"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":"2110.13905","title":"Gradient Descent on Two-layer Nets: Margin Maximization and Simplicity Bias","created":"2021-10-26","cited_by_count":83,"area":null},{"id":"2202.05928","title":"Benign Overfitting without Linearity: Neural Network Classifiers Trained by Gradient Descent for Noisy Linear Data","created":"2022-02-11","cited_by_count":74,"area":null},{"id":"2105.14602","title":"On the geometry of generalization and memorization in deep neural networks","created":"2021-05-30","cited_by_count":73,"area":null},{"id":"2210.09974","title":"Theoretical Guarantees for Permutation-Equivariant Quantum Neural Networks","created":"2022-10-18","cited_by_count":52,"area":null},{"id":"2211.11567","title":"Neural networks trained with SGD learn distributions of increasing complexity","created":"2022-11-21","cited_by_count":50,"area":null},{"id":"2210.07082","title":"Implicit Bias in Leaky ReLU Networks Trained on High-Dimensional Data","created":"2022-10-13","cited_by_count":46,"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":"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":"2304.11327","title":"Understanding and Improving Feature Learning for Out-of-Distribution Generalization","created":"2023-04-22","cited_by_count":35,"area":null},{"id":"2306.04073","title":"Patch-level Routing in Mixture-of-Experts is Provably Sample-efficient for Convolutional Neural Networks","created":"2023-06-07","cited_by_count":35,"area":"moe"},{"id":"2307.12851","title":"Early Neuron Alignment in Two-layer ReLU Networks with Small Initialization","created":"2023-07-24","cited_by_count":28,"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":"2309.04332","title":"Graph Neural Networks Use Graphs When They Shouldn't","created":"2023-09-08","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":"2106.13792","title":"Proxy Convexity: A Unified Framework for the Analysis of Neural Networks Trained by Gradient Descent","created":"2021-06-25","cited_by_count":21,"area":null},{"id":"2405.16646","title":"A Provably Effective Method for Pruning Experts in Fine-tuned Sparse Mixture-of-Experts","created":"2024-05-26","cited_by_count":21,"area":"moe"},{"id":"2106.10744","title":"On the Cryptographic Hardness of Learning Single Periodic Neurons","created":"2021-06-20","cited_by_count":20,"area":null},{"id":"2303.13500","title":"A Closer Look at Model Adaptation using Feature Distortion and Simplicity Bias","created":"2023-03-23","cited_by_count":20,"area":"mechinterp"},{"id":"2101.02533","title":"Towards Understanding Learning in Neural Networks with Linear Teachers","created":"2021-01-07","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":"2101.01152","title":"Provable Generalization of SGD-trained Neural Networks of Any Width in the Presence of Adversarial Label Noise","created":"2021-01-04","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":"2406.08654","title":"Large Stepsize Gradient Descent for Non-Homogeneous Two-Layer Networks: Margin Improvement and Fast Optimization","created":"2024-06-12","cited_by_count":17,"area":null},{"id":"2211.16667","title":"Dynamic Sparse Training via Balancing the Exploration-Exploitation Trade-off","created":"2022-11-30","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":"2207.09455","title":"To update or not to update? Neurons at equilibrium in deep models","created":"2022-07-19","cited_by_count":13,"area":null},{"id":"2302.01576","title":"ResMem: Learn what you can and memorize the rest","created":"2023-02-03","cited_by_count":13,"area":null},{"id":"2205.08099","title":"Dimensionality Reduced Training by Pruning and Freezing Parts of a Deep Neural Network, a Survey","created":"2022-05-17","cited_by_count":12,"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":"2405.17299","title":"Simplicity Bias of Two-Layer Networks beyond Linearly Separable Data","created":"2024-05-27","cited_by_count":11,"area":null},{"id":"2210.14672","title":"Sparsity in Continuous-Depth Neural Networks","created":"2022-10-26","cited_by_count":10,"area":null},{"id":"2305.19377","title":"Benign Overfitting in Deep Neural Networks under Lazy Training","created":"2023-05-30","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":"2302.05059","title":"Effects of noise on the overparametrization of quantum neural networks","created":"2023-02-10","cited_by_count":9,"area":null},{"id":"2305.16891","title":"Generalization Guarantees of Gradient Descent for Multi-Layer Neural Networks","created":"2023-05-26","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":"2306.09955","title":"Training shallow ReLU networks on noisy data using hinge loss: when do we overfit and is it benign?","created":"2023-06-16","cited_by_count":7,"area":null},{"id":"2504.04105","title":"Minimax Optimal Convergence of Gradient Descent in Logistic Regression via Large and Adaptive Stepsizes","created":"2025-04-05","cited_by_count":7,"area":null},{"id":"2108.06808","title":"Implicit Regularization of Bregman Proximal Point Algorithm and Mirror Descent on Separable Data","created":"2021-08-15","cited_by_count":6,"area":null},{"id":"2310.05337","title":"What do larger image classifiers memorise?","created":"2023-10-09","cited_by_count":6,"area":null},{"id":"2403.06903","title":"Benign overfitting in leaky ReLU networks with moderate input dimension","created":"2024-03-11","cited_by_count":6,"area":null},{"id":"2106.04186","title":"What training reveals about neural network complexity","created":"2021-06-08","cited_by_count":5,"area":null},{"id":"2101.06509","title":"Phases of learning dynamics in artificial neural networks: with or without mislabeled data","created":"2021-01-16","cited_by_count":4,"area":null},{"id":"2405.11743","title":"A General Theory for Compositional Generalization","created":"2024-05-20","cited_by_count":4,"area":null},{"id":"2406.12615","title":"When Are Bias-Free ReLU Networks Effectively Linear Networks?","created":"2024-06-18","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":"2104.11895","title":"Achieving Small Test Error in Mildly Overparameterized Neural Networks","created":"2021-04-24","cited_by_count":3,"area":null},{"id":"2310.13183","title":"Breaking through Deterministic Barriers: Randomized Pruning Mask Generation and Selection","created":"2023-10-19","cited_by_count":3,"area":null},{"id":"2311.09858","title":"Polynomially Over-Parameterized Convolutional Neural Networks Contain Structured Strong Winning Lottery Tickets","created":"2023-11-16","cited_by_count":3,"area":null},{"id":"2312.12483","title":"SCoTTi: Save Computation at Training Time with an adaptive framework","created":"2023-12-19","cited_by_count":3,"area":null},{"id":"2409.12446","title":"Neural Networks Generalize on Low Complexity Data","created":"2024-09-19","cited_by_count":3,"area":null},{"id":"2202.01210","title":"Deep Layer-wise Networks Have Closed-Form Weights","created":"2022-02-01","cited_by_count":2,"area":null},{"id":"2202.03524","title":"Finite-Sum Optimization: A New Perspective for Convergence to a Global Solution","created":"2022-02-07","cited_by_count":2,"area":null},{"id":"2206.05869","title":"On the Convergence to a Global Solution of Shuffling-Type Gradient Algorithms","created":"2022-06-13","cited_by_count":2,"area":null},{"id":"2305.17559","title":"Pruning at Initialization -- A Sketching Perspective","created":"2023-05-27","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":"2505.11370","title":"Understanding Nonlinear Implicit Bias via Region Counts in Input Space","created":"2025-05-16","cited_by_count":2,"area":null},{"id":"2601.01465","title":"Leveraging Flatness to Improve Information-Theoretic Generalization Bounds for SGD","created":"2026-01-04","cited_by_count":2,"area":null},{"id":"2602.05600","title":"On the Superlinear Relationship between SGD Noise Covariance and Loss Landscape Curvature","created":"2026-02-05","cited_by_count":2,"area":null},{"id":"2604.06515","title":"Efficient Quantization of Mixture-of-Experts with Theoretical Generalization Guarantees","created":"2026-04-07","cited_by_count":2,"area":"moe"},{"id":"2111.02154","title":"Regularization by Misclassification in ReLU Neural Networks","created":"2021-11-03","cited_by_count":1,"area":null},{"id":"2201.12052","title":"Improved Overparametrization Bounds for Global Convergence of Stochastic Gradient Descent for Shallow Neural Networks","created":"2022-01-28","cited_by_count":1,"area":null},{"id":"2211.03570","title":"Do highly over-parameterized neural networks generalize since bad solutions are rare?","created":"2022-11-07","cited_by_count":1,"area":null},{"id":"2212.02323","title":"Improved Convergence Guarantees for Shallow Neural Networks","created":"2022-12-05","cited_by_count":1,"area":null},{"id":"2403.16215","title":"Systematic construction of continuous-time neural networks for linear dynamical systems","created":"2024-03-24","cited_by_count":1,"area":null},{"id":"2409.01498","title":"A practical generalization metric for deep networks benchmarking","created":"2024-09-02","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":"2605.05659","title":"Structural Correspondence and Universal Approximation in Diagonal plus Low-Rank Neural Networks","created":"2026-05-07","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":"2201.10257","title":"PREVIS -- A Combined Machine Learning and Visual Interpolation Approach for Interactive Reverse Engineering in Assembly Quality Control","created":"2022-01-25","cited_by_count":0,"area":null},{"id":"2303.13589","title":"On the Efficacy of Generalization Error Prediction Scoring Functions","created":"2023-03-23","cited_by_count":0,"area":null},{"id":"2410.16868","title":"Rethinking generalization of classifiers in separable classes scenarios and over-parameterized regimes","created":"2024-10-22","cited_by_count":0,"area":null},{"id":"2602.00172","title":"Neuron Block Dynamics for XOR Classification with Zero-Margin","created":"2026-01-30","cited_by_count":0,"area":null},{"id":"2603.02633","title":"Robust Heterogeneous Analog-Digital Computing for Mixture-of-Experts Models with Theoretical Generalization Guarantees","created":"2026-03-03","cited_by_count":0,"area":"moe"},{"id":"2606.06764","title":"Optimal Rates for Generalization of Gradient Descent Methods with Deep Neural Networks","created":"2026-06-04","cited_by_count":0,"area":null}],"next_cursor":null}