Optimization & Theory

Accumulated Gradient Normalization ACML 2017 A Compact DNN: Approaching GoogLeNet-Level Accuracy of Classification and Domain Adaptation CVPR 2017 A Comparison of Perceptually Motivated Loss Functions for Binary Mask Estimation in Speech Separation Interspeech 2017 Active Bias: Training More Accurate Neural Networks by Emphasizing High Variance Samples NeurIPS 2017 Adaptive Relaxed ADMM: Convergence Theory and Practical Implementation CVPR 2017 ADMM without a Fixed Penalty Parameter: Faster Convergence with New Adaptive Penalization NeurIPS 2017 A Gift From Knowledge Distillation: Fast Optimization, Network Minimization and Transfer Learning CVPR 2017 A Greedy Approach for Budgeted Maximum Inner Product Search NeurIPS 2017 All You Need Is Beyond a Good Init: Exploring Better Solution for Training Extremely Deep Convolutional Neural Networks With Orthonormality and Modulation CVPR 2017 An Empirical Study on The Properties of Random Bases for Kernel Methods NeurIPS 2017 An experimental analysis of Noise-Contrastive Estimation: the noise distribution matters EACL 2017 A Non-Convex Variational Approach to Photometric Stereo Under Inaccurate Lighting CVPR 2017 Axiomatic Attribution for Deep Networks ICML 2017 Batch Renormalization: Towards Reducing Minibatch Dependence in Batch-Normalized Models NeurIPS 2017 Bayesian Compression for Deep Learning NeurIPS 2017 Beyond Filters: Compact Feature Map for Portable Deep Model ICML 2017 Can Decentralized Algorithms Outperform Centralized Algorithms? A Case Study for Decentralized Parallel Stochastic Gradient Descent NeurIPS 2017 Clipper: A Low-Latency Online Prediction Serving System NSDI 2017 Collaborative Deep Learning in Fixed Topology Networks NeurIPS 2017 Compression-aware Training of Deep Networks NeurIPS 2017 Concept Equalization to Guide Correct Training of Neural Machine Translation IJCNLP 2017 Convergence Analysis of Two-layer Neural Networks with ReLU Activation NeurIPS 2017 Convergent Block Coordinate Descent for Training Tikhonov Regularized Deep Neural Networks NeurIPS 2017 Convex Global 3D Registration With Lagrangian Duality CVPR 2017 Decoding with Finite-State Transducers on GPUs EACL 2017