Optimization & Theory

Spectrally-normalized margin bounds for neural networks NeurIPS 2017 Speed/Accuracy Trade-Offs for Modern Convolutional Object Detectors CVPR 2017 SplitNet: Learning to Semantically Split Deep Networks for Parameter Reduction and Model Parallelization ICML 2017 Straggler Mitigation in Distributed Optimization Through Data Encoding NeurIPS 2017 Structured Bayesian Pruning via Log-Normal Multiplicative Noise NeurIPS 2017 Sub-sampled Cubic Regularization for Non-convex Optimization ICML 2017 SVCCA: Singular Vector Canonical Correlation Analysis for Deep Learning Dynamics and Interpretability NeurIPS 2017 SVD-Softmax: Fast Softmax Approximation on Large Vocabulary Neural Networks NeurIPS 2017 TernGrad: Ternary Gradients to Reduce Communication in Distributed Deep Learning NeurIPS 2017 The Expressive Power of Neural Networks: A View from the Width NeurIPS 2017 The Marginal Value of Adaptive Gradient Methods in Machine Learning NeurIPS 2017 The Numerics of GANs NeurIPS 2017 The Reversible Residual Network: Backpropagation Without Storing Activations NeurIPS 2017 Towards Accurate Binary Convolutional Neural Network NeurIPS 2017 Towards Compact and Fast Neural Machine Translation Using a Combined Method EMNLP 2017 Towards Generalization and Simplicity in Continuous Control NeurIPS 2017 Training Deep Networks without Learning Rates Through Coin Betting NeurIPS 2017 Train longer, generalize better: closing the generalization gap in large batch training of neural networks NeurIPS 2017 Transfer Learning and Distillation Techniques to Improve the Acoustic Modeling of Low Resource Languages Interspeech 2017 Unfolding and Shrinking Neural Machine Translation Ensembles EMNLP 2017 Unified representation of tractography and diffusion-weighted MRI data using sparse multidimensional arrays NeurIPS 2017 Variants of RMSProp and Adagrad with Logarithmic Regret Bounds ICML 2017 Weighted-Entropy-Based Quantization for Deep Neural Networks CVPR 2017 Xception: Deep Learning With Depthwise Separable Convolutions CVPR 2017 Adaptive Newton Method for Empirical Risk Minimization to Statistical Accuracy NeurIPS 2016