Optimization & Theory

Step-Ahead Error Feedback for Distributed Training with Compressed Gradient AAAI 2021 Stochastic Anderson Mixing for Nonconvex Stochastic Optimization NeurIPS 2021 Stochastic Polyak Step-size for SGD: An Adaptive Learning Rate for Fast Convergence AISTATS 2021 Stochastic Precision Ensemble: Self-Knowledge Distillation for Quantized Deep Neural Networks AAAI 2021 Stochastic Whitening Batch Normalization CVPR 2021 Style-Aware Normalized Loss for Improving Arbitrary Style Transfer CVPR 2021 Subformer: Exploring Weight Sharing for Parameter Efficiency in Generative Transformers EMNLP 2021 Successive Halving Top-k Operator AAAI 2021 Sustainable Modular Debiasing of Language Models EMNLP 2021 SwiftNet: Real-Time Video Object Segmentation CVPR 2021 Tangent Space Backpropagation for 3D Transformation Groups CVPR 2021 Teacher Guided Neural Architecture Search for Face Recognition AAAI 2021 TensorHive: Management of Exclusive GPU Access for Distributed Machine Learning Workloads JMLR 2021 Tensor Normal Training for Deep Learning Models NeurIPS 2021 Tensor Programs IIb: Architectural Universality Of Neural Tangent Kernel Training Dynamics ICML 2021 Tensor Programs IV: Feature Learning in Infinite-Width Neural Networks ICML 2021 TenTrans High-Performance Inference Toolkit for WMT2021 Efficiency Task EMNLP 2021 Testing Cross-Database Semantic Parsers With Canonical Utterances EMNLP 2021 TextFlint: Unified Multilingual Robustness Evaluation Toolkit for Natural Language Processing ACL 2021 The balancing principle for parameter choice in distance-regularized domain adaptation NeurIPS 2021 The CODI-CRAC 2021 Shared Task on Anaphora, Bridging, and Discourse Deixis Resolution in Dialogue: A Cross-Team Analysis EMNLP 2021 The Effects of Mild Over-parameterization on the Optimization Landscape of Shallow ReLU Neural Networks COLT 2021 The Flip Side of the Reweighted Coin: Duality of Adaptive Dropout and Regularization NeurIPS 2021 The Heavy-Tail Phenomenon in SGD ICML 2021 The Heterogeneity Hypothesis: Finding Layer-Wise Differentiated Network Architectures CVPR 2021