Neural Network Optimization

Algorithmic Stability of Heavy-Tailed SGD with General Loss Functions ICML 2023 A Mini-Block Fisher Method for Deep Neural Networks AISTATS 2023 A Modern Look at the Relationship between Sharpness and Generalization ICML 2023 An Efficient Speech Separation Network Based on Recurrent Fusion Dilated Convolution and Channel Attention Interspeech 2023 An Inexact Augmented Lagrangian Algorithm for Training Leaky ReLU Neural Network with Group Sparsity JMLR 2023 An SDE for Modeling SAM: Theory and Insights ICML 2023 ASkewSGD : An Annealed interval-constrained Optimisation method to train Quantized Neural Networks AISTATS 2023 A Unified Approach to Controlling Implicit Regularization via Mirror Descent JMLR 2023 AutoInit: Analytic Signal-Preserving Weight Initialization for Neural Networks AAAI 2023 Backpropagation-Free Deep Learning with Recursive Local Representation Alignment AAAI 2023 Benign Overfitting in Deep Neural Networks under Lazy Training ICML 2023 Better Loss Landscape Visualization for Deep Neural Networks with Trajectory Information ACML 2023 Bias in Pruned Vision Models: In-Depth Analysis and Countermeasures CVPR 2023 Bi-Drop: Enhancing Fine-tuning Generalization via Synchronous sub-net Estimation and Optimization EMNLP 2023 Binarizing Sparse Convolutional Networks for Efficient Point Cloud Analysis CVPR 2023 BiSLS/SPS: Auto-tune Step Sizes for Stable Bi-level Optimization NeurIPS 2023 Boosting Inference Efficiency: Unleashing the Power of Parameter-Shared Pre-trained Language Models EMNLP 2023 Breaking through Deterministic Barriers: Randomized Pruning Mask Generation and Selection EMNLP 2023 CAME: Confidence-guided Adaptive Memory Efficient Optimization ACL 2023 Can Forward Gradient Match Backpropagation? ICML 2023 Can We Find Strong Lottery Tickets in Generative Models? AAAI 2023 Class Adaptive Network Calibration CVPR 2023 Conformal Inference is (almost) Free for Neural Networks Trained with Early Stopping ICML 2023 Convergence of Adam Under Relaxed Assumptions NeurIPS 2023 Co-Training 2L Submodels for Visual Recognition CVPR 2023