Optimization & Theory

Deep Hyperspherical Learning NeurIPS 2017 Deep Learning With Low Precision by Half-Wave Gaussian Quantization CVPR 2017 Deeply Aggregated Alternating Minimization for Image Restoration CVPR 2017 Deep Roots: Improving CNN Efficiency With Hierarchical Filter Groups CVPR 2017 Designing Energy-Efficient Convolutional Neural Networks Using Energy-Aware Pruning CVPR 2017 Differentiable Scheduled Sampling for Credit Assignment ACL 2017 DOPE: Distributed Optimization for Pairwise Energies CVPR 2017 DSAC - Differentiable RANSAC for Camera Localization CVPR 2017 Dynamic Data Selection for Neural Machine Translation EMNLP 2017 EAST: An Efficient and Accurate Scene Text Detector CVPR 2017 ECO: Efficient Convolution Operators for Tracking CVPR 2017 Efficient Attention using a Fixed-Size Memory Representation EMNLP 2017 Efficient Private ERM for Smooth Objectives IJCAI 2017 Efficient Use of Limited-Memory Accelerators for Linear Learning on Heterogeneous Systems NeurIPS 2017 Eigenvalue Decay Implies Polynomial-Time Learnability for Neural Networks NeurIPS 2017 Failures of Gradient-Based Deep Learning ICML 2017 Fast Person Re-Identification via Cross-Camera Semantic Binary Transformation CVPR 2017 Fast, Sample-Efficient Algorithms for Structured Phase Retrieval NeurIPS 2017 Filter Flow Made Practical: Massively Parallel and Lock-Free CVPR 2017 Fixed-Point Factorized Networks CVPR 2017 Fixed-Rank Approximation of a Positive-Semidefinite Matrix from Streaming Data NeurIPS 2017 Flexible Spatio-Temporal Networks for Video Prediction CVPR 2017 Flexpoint: An Adaptive Numerical Format for Efficient Training of Deep Neural Networks NeurIPS 2017 Follow the Compressed Leader: Faster Online Learning of Eigenvectors and Faster MMWU ICML 2017 Follow the Moving Leader in Deep Learning ICML 2017