Optimization & Theory

Assessing Human-Parity in Machine Translation on the Segment Level EMNLP 2020 Assessing Local Generalization Capability in Deep Models AISTATS 2020 Assessment of DistilBERT performance on Named Entity Recognition task for the detection of Protected Health Information and medical concepts EMNLP 2020 Associative Memory in Iterated Overparameterized Sigmoid Autoencoders ICML 2020 A Streaming Approach For Efficient Batched Beam Search EMNLP 2020 Asymptotic normality and confidence intervals for derivatives of 2-layers neural network in the random features model NeurIPS 2020 Asymptotics of Wide Networks from Feynman Diagrams ICLR 2020 A Tensor Compiler for Unified Machine Learning Prediction Serving OSDI 2020 Attention is Not Only a Weight: Analyzing Transformers with Vector Norms EMNLP 2020 Attentive Pooling with Learnable Norms for Text Representation ACL 2020 Attribution in Scale and Space CVPR 2020 Augment Your Batch: Improving Generalization Through Instance Repetition CVPR 2020 AutoCompress: An Automatic DNN Structured Pruning Framework for Ultra-High Compression Rates AAAI 2020 AutoDAL: Distributed Active Learning with Automatic Hyperparameter Selection AAAI 2020 Autolabeling 3D Objects With Differentiable Rendering of SDF Shape Priors CVPR 2020 Automatic Building and Labeling of HD Maps with Deep Learning AAAI 2020 Automatic Neural Network Compression by Sparsity-Quantization Joint Learning: A Constrained Optimization-Based Approach CVPR 2020 AutoML-Zero: Evolving Machine Learning Algorithms From Scratch ICML 2020 AutoQ: Automated Kernel-Wise Neural Network Quantization ICLR 2020 AutoShrink: A Topology-Aware NAS for Discovering Efficient Neural Architecture AAAI 2020 Auto-Tuning Structured Light by Optical Stochastic Gradient Descent CVPR 2020 BaKer-Nets: Bayesian Random Kernel Mapping Networks IJCAI 2020 Batch normalization provably avoids ranks collapse for randomly initialised deep networks NeurIPS 2020 Bayesian Bits: Unifying Quantization and Pruning NeurIPS 2020 Benchmarking Deep Inverse Models over time, and the Neural-Adjoint method NeurIPS 2020