relu network

Adversarial Examples Exist in Two-Layer ReLU Networks for Low Dimensional Linear Subspaces NeurIPS 2023 An Exact Poly-Time Membership-Queries Algorithm for Extracting a Three-Layer ReLU Network ICLR 2023 Approximation and non-parametric estimation of functions over high-dimensional spheres via deep ReLU networks ICLR 2023 Benign Overfitting in Linear Classifiers and Leaky ReLU Networks from KKT Conditions for Margin Maximization COLT 2023 Certified Invertibility in Neural Networks via Mixed-Integer Programming L4DC 2023 Excess Risk of Two-Layer ReLU Neural Networks in Teacher-Student Settings and its Superiority to Kernel Methods ICLR 2023 From Tempered to Benign Overfitting in ReLU Neural Networks NeurIPS 2023 Implicit Bias of Gradient Descent for Two-layer ReLU and Leaky ReLU Networks on Nearly-orthogonal Data NeurIPS 2023 Implicit Regularization Towards Rank Minimization in ReLU Networks ALT 2023 Investigating how ReLU-networks encode symmetries NeurIPS 2023 Learning a 1-layer conditional generative model in total variation NeurIPS 2023 Learning a Neuron by a Shallow ReLU Network: Dynamics and Implicit Bias for Correlated Inputs NeurIPS 2023 Learning Narrow One-Hidden-Layer ReLU Networks COLT 2023 Learning ReLU networks to high uniform accuracy is intractable ICLR 2023 Maximal Initial Learning Rates in Deep ReLU Networks ICML 2023 Memorization Capacity of Neural Networks with Conditional Computation ICLR 2023 Model-Based Control with Sparse Neural Dynamics NeurIPS 2023 Norm-based Generalization Bounds for Sparse Neural Networks NeurIPS 2023 On Enhancing Expressive Power via Compositions of Single Fixed-Size ReLU Network ICML 2023 Optimal Sets and Solution Paths of ReLU Networks ICML 2023 Path Regularization: A Convexity and Sparsity Inducing Regularization for Parallel ReLU Networks NeurIPS 2023 Penalising the biases in norm regularisation enforces sparsity NeurIPS 2023 Polyhedral Complex Extraction from ReLU Networks using Edge Subdivision ICML 2023 Provable Advantage of Curriculum Learning on Parity Targets with Mixed Inputs NeurIPS 2023 Quasi-Equivalence between Width and Depth of Neural Networks JMLR 2023