Neural Network Optimization

Finite-Sample Analysis of Learning High-Dimensional Single ReLU Neuron ICML 2023 Fisher-Legendre (FishLeg) optimization of deep neural networks ICLR 2023 Fixed-Weight Difference Target Propagation AAAI 2023 Fixing the NTK: From Neural Network Linearizations to Exact Convex Programs NeurIPS 2023 FlatMatch: Bridging Labeled Data and Unlabeled Data with Cross-Sharpness for Semi-Supervised Learning NeurIPS 2023 Flatness-Aware Minimization for Domain Generalization ICCV 2023 FLOAT: Fast Learnable Once-for-All Adversarial Training for Tunable Trade-Off Between Accuracy and Robustness WACV 2023 Focused Prefix Tuning for Controllable Text Generation ACL 2023 Focus Your Attention (with Adaptive IIR Filters) EMNLP 2023 Frustratingly Easy Regularization on Representation Can Boost Deep Reinforcement Learning CVPR 2023 Fundamental Limits of Two-layer Autoencoders, and Achieving Them with Gradient Methods ICML 2023 GeNAS: Neural Architecture Search with Better Generalization IJCAI 2023 Generalization bounds for neural ordinary differential equations and deep residual networks NeurIPS 2023 Generalized Differentiable RANSAC ICCV 2023 Generalized Polyak Step Size for First Order Optimization with Momentum ICML 2023 GEQ: Gaussian Kernel Inspired Equilibrium Models NeurIPS 2023 Global Convergence Analysis of Local SGD for Two-layer Neural Network without Overparameterization NeurIPS 2023 Global Convergence of Over-parameterized Deep Equilibrium Models AISTATS 2023 Global Optimization with Parametric Function Approximation ICML 2023 Going Beyond Linear Mode Connectivity: The Layerwise Linear Feature Connectivity NeurIPS 2023 Gradient Descent Finds the Global Optima of Two-Layer Physics-Informed Neural Networks ICML 2023 Gradient Descent in Neural Networks as Sequential Learning in Reproducing Kernel Banach Space ICML 2023 Gradient Descent Monotonically Decreases the Sharpness of Gradient Flow Solutions in Scalar Networks and Beyond ICML 2023 Gradient Flossing: Improving Gradient Descent through Dynamic Control of Jacobians NeurIPS 2023 Gradient Gating for Deep Multi-Rate Learning on Graphs ICLR 2023