Neural Network Optimization

Learning Hard Retrieval Decoder Attention for Transformers EMNLP 2021 Learning Latent Architectural Distribution in Differentiable Neural Architecture Search via Variational Information Maximization ICCV 2021 Learning Neural Network Subspaces ICML 2021 Learning the Non-Differentiable Optimization for Blind Super-Resolution CVPR 2021 Learning to Defend by Learning to Attack AISTATS 2021 Learning with Generated Teammates to Achieve Type-Free Ad-Hoc Teamwork IJCAI 2021 Learning with Gradient Descent and Weakly Convex Losses AISTATS 2021 Learning with Hyperspherical Uniformity AISTATS 2021 Learning with Retrospection AAAI 2021 Learn To Match: Automatic Matching Network Design for Visual Tracking ICCV 2021 LeeBERT: Learned Early Exit for BERT with cross-level optimization ACL 2021 Length-Adaptive Transformer: Train Once with Length Drop, Use Anytime with Search ACL 2021 Linear Convergence of Gradient Methods for Estimating Structured Transition Matrices in High-dimensional Vector Autoregressive Models NeurIPS 2021 Linear Transformers Are Secretly Fast Weight Programmers ICML 2021 Local Temperature Scaling for Probability Calibration ICCV 2021 Long-Span Summarization via Local Attention and Content Selection ACL 2021 Loss Surface Simplexes for Mode Connecting Volumes and Fast Ensembling ICML 2021 Lottery Ticket Preserves Weight Correlation: Is It Desirable or Not? ICML 2021 Low-Fidelity Video Encoder Optimization for Temporal Action Localization NeurIPS 2021 LQF: Linear Quadratic Fine-Tuning CVPR 2021 Luna: Linear Unified Nested Attention NeurIPS 2021 MALI: A memory efficient and reverse accurate integrator for Neural ODEs ICLR 2021 Memory-Gated Recurrent Networks AAAI 2021 MEST: Accurate and Fast Memory-Economic Sparse Training Framework on the Edge NeurIPS 2021 Meta-Learning Bidirectional Update Rules ICML 2021