Optimization & Theory

Are ResNets Provably Better than Linear Predictors? NeurIPS 2018 A Theoretical Explanation for Perplexing Behaviors of Backpropagation-based Visualizations ICML 2018 ATOMO: Communication-efficient Learning via Atomic Sparsification NeurIPS 2018 Attaining the Unattainable? Reassessing Claims of Human Parity in Neural Machine Translation EMNLP 2018 A Two-Step Computation of the Exact GAN Wasserstein Distance ICML 2018 Backpropagation with Callbacks: Foundations for Efficient and Expressive Differentiable Programming NeurIPS 2018 Back to Basics: Benchmarking Canonical Evolution Strategies for Playing Atari IJCAI 2018 Baseline: A Library for Rapid Modeling, Experimentation and Development of Deep Learning Algorithms targeting NLP ACL 2018 Beyond Trade-Off: Accelerate FCN-Based Face Detector With Higher Accuracy CVPR 2018 Blind Deconvolutional Phase Retrieval via Convex Programming NeurIPS 2018 BlockDrop: Dynamic Inference Paths in Residual Networks CVPR 2018 BML: A High-performance, Low-cost Gradient Synchronization Algorithm for DML Training NeurIPS 2018 Boosting Adversarial Attacks With Momentum CVPR 2018 Bounds on the Approximation Power of Feedforward Neural Networks ICML 2018 BPGrad: Towards Global Optimality in Deep Learning via Branch and Pruning CVPR 2018 Breaking the Beam Search Curse: A Study of (Re-)Scoring Methods and Stopping Criteria for Neural Machine Translation EMNLP 2018 Byzantine Stochastic Gradient Descent NeurIPS 2018 Can We Gain More from Orthogonality Regularizations in Training Deep Networks? NeurIPS 2018 ClcNet: Improving the Efficiency of Convolutional Neural Network Using Channel Local Convolutions CVPR 2018 CLIP-Q: Deep Network Compression Learning by In-Parallel Pruning-Quantization CVPR 2018 Collaboratively Weighting Deep and Classic Representation via l_2 Regularization for Image Classification ACML 2018 Communication Compression for Decentralized Training NeurIPS 2018 Compact Personalized Models for Neural Machine Translation EMNLP 2018 Compare, Compress and Propagate: Enhancing Neural Architectures with Alignment Factorization for Natural Language Inference EMNLP 2018 Composing Finite State Transducers on GPUs ACL 2018