neural network optimization

Fed-LAMB: Layer-wise and Dimension-wise Locally Adaptive Federated Learning UAI 2023 FedNAR: Federated Optimization with Normalized Annealing Regularization NeurIPS 2023 FemtoDet: An Object Detection Baseline for Energy Versus Performance Tradeoffs ICCV 2023 Finite-Sample Analysis of Learning High-Dimensional Single ReLU Neuron ICML 2023 Fixed-Weight Difference Target Propagation AAAI 2023 Flatness-Aware Minimization for Domain Generalization ICCV 2023 FLatten Transformer: Vision Transformer using Focused Linear Attention ICCV 2023 FlexRound: Learnable Rounding based on Element-wise Division for Post-Training Quantization ICML 2023 FouriDown: Factoring Down-Sampling into Shuffling and Superposing NeurIPS 2023 Git Re-Basin: Merging Models modulo Permutation Symmetries ICLR 2023 Global Convergence of Over-parameterized Deep Equilibrium Models AISTATS 2023 Gradient Ascent Post-training Enhances Language Model Generalization ACL 2023 Gradient Descent Monotonically Decreases the Sharpness of Gradient Flow Solutions in Scalar Networks and Beyond ICML 2023 GradMA: A Gradient-Memory-Based Accelerated Federated Learning With Alleviated Catastrophic Forgetting CVPR 2023 How much does Initialization Affect Generalization? ICML 2023 Hungry Hungry Hippos: Towards Language Modeling with State Space Models ICLR 2023 Hyperblock Floating Point: Generalised Quantization Scheme for Gradient and Inference Computation WACV 2023 HyperRouter: Towards Efficient Training and Inference of Sparse Mixture of Experts EMNLP 2023 Implicit Bias of Gradient Descent for Two-layer ReLU and Leaky ReLU Networks on Nearly-orthogonal Data NeurIPS 2023 Implicit Jacobian regularization weighted with impurity of probability output ICML 2023 Implicit Stochastic Gradient Descent for Training Physics-Informed Neural Networks AAAI 2023 Improved Logical Reasoning of Language Models via Differentiable Symbolic Programming ACL 2023 Improving Adversarial Robustness via Information Bottleneck Distillation NeurIPS 2023 Improving generalization in large langue model by learning prefix subspaces EMNLP 2023 Incorporating Syntactic Knowledge into Pre-trained Language Model using Optimization for Overcoming Catastrophic Forgetting EMNLP 2023