Optimization & Theory

Learning to solve TV regularised problems with unrolled algorithms NeurIPS 2020 Leveraging Filter Correlations for Deep Model Compression WACV 2020 Light Field Spatial Super-Resolution via Deep Combinatorial Geometry Embedding and Structural Consistency Regularization CVPR 2020 Light Multi-Segment Activation for Model Compression AAAI 2020 Linear Context Transform Block AAAI 2020 Linear Convergence of Randomized Primal-Dual Coordinate Method for Large-scale Linear Constrained Convex Programming ICML 2020 Lipschitz-Certifiable Training with a Tight Outer Bound NeurIPS 2020 Lipschitz Constrained Parameter Initialization for Deep Transformers ACL 2020 Load What You Need: Smaller Versions of Mutililingual BERT EMNLP 2020 Local Binary Pattern Networks WACV 2020 Local Regularizer Improves Generalization AAAI 2020 Long Document Ranking with Query-Directed Sparse Transformer EMNLP 2020 Losing Heads in the Lottery: Pruning Transformer Attention in Neural Machine Translation EMNLP 2020 Low Bias Low Variance Gradient Estimates for Boolean Stochastic Networks ICML 2020 Low-Rank Compression of Neural Nets: Learning the Rank of Each Layer CVPR 2020 LSM: Learning Subspace Minimization for Low-Level Vision CVPR 2020 LSTM Neural Networks: Input to State Stability and Probabilistic Safety Verification L4DC 2020 MAGSAC++, a Fast, Reliable and Accurate Robust Estimator CVPR 2020 Manifold Identification for Ultimately Communication-Efficient Distributed Optimization ICML 2020 Masking as an Efficient Alternative to Finetuning for Pretrained Language Models EMNLP 2020 Maximum-and-Concatenation Networks ICML 2020 MemNAS: Memory-Efficient Neural Architecture Search With Grow-Trim Learning CVPR 2020 MiLeNAS: Efficient Neural Architecture Search via Mixed-Level Reformulation CVPR 2020 Minibatch vs Local SGD for Heterogeneous Distributed Learning NeurIPS 2020 MiniLM: Deep Self-Attention Distillation for Task-Agnostic Compression of Pre-Trained Transformers NeurIPS 2020