Optimization & Theory

ScaleKD: Distilling Scale-Aware Knowledge in Small Object Detector CVPR 2023 Scaling Law for Document Neural Machine Translation EMNLP 2023 Scaling Laws for BERT in Low-Resource Settings ACL 2023 Scaling Laws for Discriminative Speech Recognition Rescoring Models Interspeech 2023 Scaling Laws for Generative Mixed-Modal Language Models ICML 2023 Scaling Laws for Multilingual Neural Machine Translation ICML 2023 Scaling Laws vs Model Architectures: How does Inductive Bias Influence Scaling? EMNLP 2023 Scaling up and Stabilizing Differentiable Planning with Implicit Differentiation ICLR 2023 Scaling Vision-Language Models with Sparse Mixture of Experts EMNLP 2023 SCConv: Spatial and Channel Reconstruction Convolution for Feature Redundancy CVPR 2023 Scissorhands: Exploiting the Persistence of Importance Hypothesis for LLM KV Cache Compression at Test Time NeurIPS 2023 SCoMoE: Efficient Mixtures of Experts with Structured Communication ICLR 2023 Search-Map-Search: A Frame Selection Paradigm for Action Recognition CVPR 2023 Second-order regression models exhibit progressive sharpening to the edge of stability ICML 2023 "Seeing" Electric Network Frequency From Events CVPR 2023 Segmented Recurrent Transformer: An Efficient Sequence-to-Sequence Model EMNLP 2023 Selectivity Drives Productivity: Efficient Dataset Pruning for Enhanced Transfer Learning NeurIPS 2023 Self-Evolution Learning for Discriminative Language Model Pretraining ACL 2023 Self-Supervised Primal-Dual Learning for Constrained Optimization AAAI 2023 Separable Physics-Informed Neural Networks NeurIPS 2023 Sequence Parallelism: Long Sequence Training from System Perspective ACL 2023 Sequential Integrated Gradients: a simple but effective method for explaining language models ACL 2023 SGD learning on neural networks: leap complexity and saddle-to-saddle dynamics COLT 2023 (S)GD over Diagonal Linear Networks: Implicit bias, Large Stepsizes and Edge of Stability NeurIPS 2023 SGD with AdaGrad Stepsizes: Full Adaptivity with High Probability to Unknown Parameters, Unbounded Gradients and Affine Variance ICML 2023