Optimization & Theory

Limitations of Post-Hoc Feature Alignment for Robustness CVPR 2021 Linear Convergence of Gradient Methods for Estimating Structured Transition Matrices in High-dimensional Vector Autoregressive Models NeurIPS 2021 Linear Convergent Decentralized Optimization with Compression ICLR 2021 Linearly Replaceable Filters for Deep Network Channel Pruning AAAI 2021 Liquid Time-constant Networks AAAI 2021 Locally Free Weight Sharing for Network Width Search ICLR 2021 LocalNewton: Reducing communication rounds for distributed learning UAI 2021 Local Signal Adaptivity: Provable Feature Learning in Neural Networks Beyond Kernels NeurIPS 2021 Log-Likelihood-Ratio Cost Function as Objective Loss for Speaker Verification Systems Interspeech 2021 Long Range Arena : A Benchmark for Efficient Transformers ICLR 2021 Lossless Compression of Structured Convolutional Models via Lifting ICLR 2021 Loss Surface Simplexes for Mode Connecting Volumes and Fast Ensembling ICML 2021 Lower Perplexity is Not Always Human-Like ACL 2021 Low-Precision Reinforcement Learning: Running Soft Actor-Critic in Half Precision ICML 2021 Low-Rank Sinkhorn Factorization ICML 2021 Low Resource Quadratic Forms for Knowledge Graph Embeddings EMNLP 2021 LPSNet: A Lightweight Solution for Fast Panoptic Segmentation CVPR 2021 LQF: Linear Quadratic Fine-Tuning CVPR 2021 Manifold Regularized Dynamic Network Pruning CVPR 2021 Marginalized Stochastic Natural Gradients for Black-Box Variational Inference ICML 2021 Marginal Utility Diminishes: Exploring the Minimum Knowledge for BERT Knowledge Distillation ACL 2021 MARINA: Faster Non-Convex Distributed Learning with Compression ICML 2021 Mars Image Content Classification: Three Years of NASA Deployment and Recent Advances AAAI 2021 Mask-ToF: Learning Microlens Masks for Flying Pixel Correction in Time-of-Flight Imaging CVPR 2021 MATE: Multi-view Attention for Table Transformer Efficiency EMNLP 2021