two-layer neural network

Learning Expressive Random Feature Models via Parametrized Activations UAI 2026 Adversarial Training in High-Dimensional Regression: Generated Data and Neural Networks AISTATS 2025 Analyzing Neural Scaling Laws in Two-Layer Networks with Power-Law Data Spectra ICLR 2025 How Gradient descent balances features: A dynamical analysis for two-layer neural networks ICLR 2025 Learning sum of diverse features: computational hardness and efficient gradient-based training for ridge combinations COLT 2024 Mean-field Analysis on Two-layer Neural Networks from a Kernel Perspective ICML 2024 Online Learning and Information Exponents: The Importance of Batch size & Time/Complexity Tradeoffs ICML 2024 On the Sample Complexity of Two-Layer Networks: Lipschitz Vs. Element-Wise Lipschitz Activation ALT 2024 Sampling from the Mean-Field Stationary Distribution COLT 2024 Simplicity Bias via Global Convergence of Sharpness Minimization ICML 2024 Convergence of mean-field Langevin dynamics: time-space discretization, stochastic gradient, and variance reduction NeurIPS 2023 Efficient displacement convex optimization with particle gradient descent ICML 2023 Entropic Fictitious Play for Mean Field Optimization Problem JMLR 2023 Fast Convergence in Learning Two-Layer Neural Networks with Separable Data AAAI 2023 Global Convergence Analysis of Local SGD for Two-layer Neural Network without Overparameterization NeurIPS 2023 Intrinsic dimensionality and generalization properties of the R-norm inductive bias COLT 2023 AdaLoss: A Computationally-Efficient and Provably Convergent Adaptive Gradient Method AAAI 2022 Benign Overfitting without Linearity: Neural Network Classifiers Trained by Gradient Descent for Noisy Linear Data COLT 2022 Fast Convex Optimization for Two-Layer ReLU Networks: Equivalent Model Classes and Cone Decompositions ICML 2022 Neural Networks can Learn Representations with Gradient Descent COLT 2022 The merged-staircase property: a necessary and nearly sufficient condition for SGD learning of sparse functions on two-layer neural networks COLT 2022 Two-layer neural network on infinite dimensional data: global optimization guarantee in the mean-field regime NeurIPS 2022 A Law of Robustness for Two-Layers Neural Networks COLT 2021 A Local Convergence Theory for Mildly Over-Parameterized Two-Layer Neural Network COLT 2021 A Priori Generalization Analysis of the Deep Ritz Method for Solving High Dimensional Elliptic Partial Differential Equations COLT 2021