Optimization & Theory

Beyond Uniform Smoothness: A Stopped Analysis of Adaptive SGD COLT 2023 Bias in Pruned Vision Models: In-Depth Analysis and Countermeasures CVPR 2023 BiBench: Benchmarking and Analyzing Network Binarization ICML 2023 Bi-directional Masks for Efficient N:M Sparse Training ICML 2023 Bi-Drop: Enhancing Fine-tuning Generalization via Synchronous sub-net Estimation and Optimization EMNLP 2023 Bi-level Finetuning with Task-dependent Similarity Structure for Low-resource Training ACL 2023 BiMatting: Efficient Video Matting via Binarization NeurIPS 2023 Binarized Spectral Compressive Imaging NeurIPS 2023 Binarizing Sparse Convolutional Networks for Efficient Point Cloud Analysis CVPR 2023 Binary and Ternary Natural Language Generation ACL 2023 Birder: Communication-Efficient 1-bit Adaptive Optimizer for Practical Distributed DNN Training NeurIPS 2023 BiSLS/SPS: Auto-tune Step Sizes for Stable Bi-level Optimization NeurIPS 2023 Bit Allocation using Optimization ICML 2023 Bit-Shrinking: Limiting Instantaneous Sharpness for Improving Post-Training Quantization CVPR 2023 BiViT: Extremely Compressed Binary Vision Transformers ICCV 2023 Black-Box Tuning of Vision-Language Models with Effective Gradient Approximation EMNLP 2023 Blank Collapse: Compressing CTC Emission for the Faster Decoding Interspeech 2023 Boosted Dynamic Neural Networks AAAI 2023 Boosting Accuracy and Robustness of Student Models via Adaptive Adversarial Distillation CVPR 2023 Boosting Graph Neural Networks via Adaptive Knowledge Distillation AAAI 2023 Boosting Inference Efficiency: Unleashing the Power of Parameter-Shared Pre-trained Language Models EMNLP 2023 Boundary Unlearning: Rapid Forgetting of Deep Networks via Shifting the Decision Boundary CVPR 2023 Breaking Correlation Shift via Conditional Invariant Regularizer ICLR 2023 Breaking through Deterministic Barriers: Randomized Pruning Mask Generation and Selection EMNLP 2023 Bridging Precision and Confidence: A Train-Time Loss for Calibrating Object Detection CVPR 2023