Optimization & Theory

Step Size Matters in Deep Learning NeurIPS 2018 Stochastic Cubic Regularization for Fast Nonconvex Optimization NeurIPS 2018 Stochastic Downsampling for Cost-Adjustable Inference and Improved Regularization in Convolutional Networks CVPR 2018 StrassenNets: Deep Learning with a Multiplication Budget ICML 2018 Stronger Generalization Bounds for Deep Nets via a Compression Approach ICML 2018 Structured Local Minima in Sparse Blind Deconvolution NeurIPS 2018 Supervised autoencoders: Improving generalization performance with unsupervised regularizers NeurIPS 2018 Synaptic Strength For Convolutional Neural Network NeurIPS 2018 Temporal Noise Shaping with Companding Interspeech 2018 The Convergence of Sparsified Gradient Methods NeurIPS 2018 The Effect of Network Width on the Performance of Large-batch Training NeurIPS 2018 The emergence of spectral universality in deep networks AISTATS 2018 The Implicit Bias of Gradient Descent on Separable Data ICLR 2018 The Implicit Bias of Gradient Descent on Separable Data JMLR 2018 The Karlsruhe Institute of Technology Systems for the News Translation Task in WMT 2018 EMNLP 2018 Theoretical Linear Convergence of Unfolded ISTA and Its Practical Weights and Thresholds NeurIPS 2018 The Physical Systems Behind Optimization Algorithms NeurIPS 2018 The power of deeper networks for expressing natural functions ICLR 2018 The Price of Privacy for Low-rank Factorization NeurIPS 2018 The Spectrum of the Fisher Information Matrix of a Single-Hidden-Layer Neural Network NeurIPS 2018 Token-level and sequence-level loss smoothing for RNN language models ACL 2018 Toward Designing Convergent Deep Operator Splitting Methods for Task-specific Nonconvex Optimization IJCAI 2018 Towards better understanding of gradient-based attribution methods for Deep Neural Networks ICLR 2018 Towards Dynamic Computation Graphs via Sparse Latent Structure EMNLP 2018 Towards Effective Low-Bitwidth Convolutional Neural Networks CVPR 2018