Optimization & Theory

Large-batch Optimization for Dense Visual Predictions: Training Faster R-CNN in 4.2 Minutes NeurIPS 2022 Large Learning Rate Tames Homogeneity: Convergence and Balancing Effect ICLR 2022 Large-Scale Graph Neural Architecture Search ICML 2022 Large-scale Stochastic Optimization of NDCG Surrogates for Deep Learning with Provable Convergence ICML 2022 Latency-aware Spatial-wise Dynamic Networks NeurIPS 2022 LayerConnect: Hypernetwork-Assisted Inter-Layer Connector to Enhance Parameter Efficiency COLING 2022 Layer Freezing & Data Sieving: Missing Pieces of a Generic Framework for Sparse Training NeurIPS 2022 Layer-wise Adaptive Graph Convolution Networks Using Generalized Pagerank ACML 2022 LC-FDNet: Learned Lossless Image Compression With Frequency Decomposition Network CVPR 2022 Leaner and Faster: Two-Stage Model Compression for Lightweight Text-Image Retrieval NAACL 2022 Learning Based Multi-Modality Image and Video Compression CVPR 2022 Learning by Directional Gradient Descent ICLR 2022 Learning Deep Input-Output Stable Dynamics NeurIPS 2022 Learning dynamics of deep linear networks with multiple pathways NeurIPS 2022 Learning Efficient Vision Transformers via Fine-Grained Manifold Distillation NeurIPS 2022 Learning Features with Parameter-Free Layers ICLR 2022 Learning Rates as a Function of Batch Size: A Random Matrix Theory Approach to Neural Network Training JMLR 2022 Learning sparse features can lead to overfitting in neural networks NeurIPS 2022 Learning to Reason with Neural Networks: Generalization, Unseen Data and Boolean Measures NeurIPS 2022 Learning to Win Lottery Tickets in BERT Transfer via Task-agnostic Mask Training NAACL 2022 Legal-Tech Open Diaries: Lesson learned on how to develop and deploy light-weight models in the era of humongous Language Models EMNLP 2022 Less Is More: Pay Less Attention in Vision Transformers AAAI 2022 Less is More: Summary of Long Instructions is Better for Program Synthesis EMNLP 2022 Leveraging Inter-Layer Dependency for Post -Training Quantization NeurIPS 2022 Lightweight Projective Derivative Codes for Compressed Asynchronous Gradient Descent ICML 2022