Optimization & Theory

Doubly Sparse Asynchronous Learning for Stochastic Composite Optimization IJCAI 2022 Down and Across: Introducing Crossword-Solving as a New NLP Benchmark ACL 2022 DQ-BART: Efficient Sequence-to-Sequence Model via Joint Distillation and Quantization ACL 2022 DR3: Value-Based Deep Reinforcement Learning Requires Explicit Regularization ICLR 2022 DRAGONN: Distributed Randomized Approximate Gradients of Neural Networks ICML 2022 DropCov: A Simple yet Effective Method for Improving Deep Architectures NeurIPS 2022 Dropout as a Regularizer of Interaction Effects AISTATS 2022 Dual Lottery Ticket Hypothesis ICLR 2022 Dual Temperature Helps Contrastive Learning Without Many Negative Samples: Towards Understanding and Simplifying MoCo CVPR 2022 Dynamically Refined Regularization for Improving Cross-corpora Hate Speech Detection ACL 2022 Dynamic Forward and Backward Sparse Training (DFBST): Accelerated Deep Learning through Completely Sparse Training Schedule ACML 2022 Dynamic Programming in Rank Space: Scaling Structured Inference with Low-Rank HMMs and PCFGs NAACL 2022 Dynamics of SGD with Stochastic Polyak Stepsizes: Truly Adaptive Variants and Convergence to Exact Solution NeurIPS 2022 DyRep: Bootstrapping Training With Dynamic Re-Parameterization CVPR 2022 Early-Bird GCNs: Graph-Network Co-optimization towards More Efficient GCN Training and Inference via Drawing Early-Bird Lottery Tickets AAAI 2022 Earthformer: Exploring Space-Time Transformers for Earth System Forecasting NeurIPS 2022 EcoFormer: Energy-Saving Attention with Linear Complexity NeurIPS 2022 ED2LM: Encoder-Decoder to Language Model for Faster Document Re-ranking Inference ACL 2022 EdgeFormer: A Parameter-Efficient Transformer for On-Device Seq2seq Generation EMNLP 2022 Edinburgh’s Submission to the WMT 2022 Efficiency Task EMNLP 2022 EF-BV: A Unified Theory of Error Feedback and Variance Reduction Mechanisms for Biased and Unbiased Compression in Distributed Optimization NeurIPS 2022 Effects of Data Geometry in Early Deep Learning NeurIPS 2022 Efficient Adversarial Training with Robust Early-Bird Tickets EMNLP 2022 Efficient and Accurate Conversion of Spiking Neural Network with Burst Spikes IJCAI 2022 Efficient and Scalable Graph Pattern Mining on GPUs OSDI 2022