Optimization & Theory

Tencent’s Multilingual Machine Translation System for WMT22 Large-Scale African Languages EMNLP 2022 Tensor Wheel Decomposition and Its Tensor Completion Application NeurIPS 2022 TextFusion: Privacy-Preserving Pre-trained Model Inference via Token Fusion EMNLP 2022 TextPruner: A Model Pruning Toolkit for Pre-Trained Language Models ACL 2022 The alignment property of SGD noise and how it helps select flat minima: A stability analysis NeurIPS 2022 The Architectural Bottleneck Principle EMNLP 2022 The Combinatorial Brain Surgeon: Pruning Weights That Cancel One Another in Neural Networks ICML 2022 The Curse of Unrolling: Rate of Differentiating Through Optimization NeurIPS 2022 The Devil in Linear Transformer EMNLP 2022 The DEVIL Is in the Details: A Diagnostic Evaluation Benchmark for Video Inpainting CVPR 2022 The Devil is in the Details: On the Pitfalls of Vocabulary Selection in Neural Machine Translation NAACL 2022 The Effect of Manifold Entanglement and Intrinsic Dimensionality on Learning AAAI 2022 The Effects of Invertibility on the Representational Complexity of Encoders in Variational Autoencoders ICLR 2022 The Effects of Regularization and Data Augmentation are Class Dependent NeurIPS 2022 The Fast Kernel Transform AISTATS 2022 The Importance of Being Parameters: An Intra-Distillation Method for Serious Gains EMNLP 2022 The merged-staircase property: a necessary and nearly sufficient condition for SGD learning of sparse functions on two-layer neural networks COLT 2022 The Neural Covariance SDE: Shaped Infinite Depth-and-Width Networks at Initialization NeurIPS 2022 The Neural Race Reduction: Dynamics of Abstraction in Gated Networks ICML 2022 The Optimal BERT Surgeon: Scalable and Accurate Second-Order Pruning for Large Language Models EMNLP 2022 Theoretically Provable Spiking Neural Networks NeurIPS 2022 The Pitfalls of Regularization in Off-Policy TD Learning NeurIPS 2022 The price of ignorance: how much does it cost to forget noise structure in low-rank matrix estimation? NeurIPS 2022 The Principle of Diversity: Training Stronger Vision Transformers Calls for Reducing All Levels of Redundancy CVPR 2022 The Role of Adaptive Optimizers for Honest Private Hyperparameter Selection AAAI 2022