Optimization & Theory

Treeformer: Dense Gradient Trees for Efficient Attention Computation ICLR 2023 Tunable Convolutions With Parametric Multi-Loss Optimization CVPR 2023 Tuning Frequency Bias in Neural Network Training with Nonuniform Data ICLR 2023 Two Losses Are Better Than One: Faster Optimization Using a Cheaper Proxy ICML 2023 Two-Way Multi-Label Loss CVPR 2023 UINAUIL: A Unified Benchmark for Italian Natural Language Understanding ACL 2023 Ultra Dual-Path Compression For Joint Echo Cancellation And Noise Suppression Interspeech 2023 Unbiased Compression Saves Communication in Distributed Optimization: When and How Much? NeurIPS 2023 Uncovering Hidden Consequences of Pre-training Objectives in Sequence-to-Sequence Models ACL 2023 Understanding Gradient Regularization in Deep Learning: Efficient Finite-Difference Computation and Implicit Bias ICML 2023 Understanding Imbalanced Semantic Segmentation Through Neural Collapse CVPR 2023 Understanding Incremental Learning of Gradient Descent: A Fine-grained Analysis of Matrix Sensing ICML 2023 Understanding Int4 Quantization for Language Models: Latency Speedup, Composability, and Failure Cases ICML 2023 Understanding Multi-phase Optimization Dynamics and Rich Nonlinear Behaviors of ReLU Networks NeurIPS 2023 Understanding Neural Network Binarization with Forward and Backward Proximal Quantizers NeurIPS 2023 Understanding Representation Learnability of Nonlinear Self-Supervised Learning AAAI 2023 Unified Data-Free Compression: Pruning and Quantization without Fine-Tuning ICCV 2023 Uniform-in-time propagation of chaos for the mean-field gradient Langevin dynamics ICLR 2023 Unlearning Bias in Language Models by Partitioning Gradients ACL 2023 Unlimiformer: Long-Range Transformers with Unlimited Length Input NeurIPS 2023 Unlocking Deterministic Robustness Certification on ImageNet NeurIPS 2023 Unlocking Feature Visualization for Deep Network with MAgnitude Constrained Optimization NeurIPS 2023 Unveiling The Mask of Position-Information Pattern Through the Mist of Image Features ICML 2023 UPop: Unified and Progressive Pruning for Compressing Vision-Language Transformers ICML 2023 UPSCALE: Unconstrained Channel Pruning ICML 2023