Optimization & Theory

NAIS-Net: Stable Deep Networks from Non-Autonomous Differential Equations NeurIPS 2018 NASH: Toward End-to-End Neural Architecture for Generative Semantic Hashing ACL 2018 Navigating with Graph Representations for Fast and Scalable Decoding of Neural Language Models NeurIPS 2018 NEON2: Finding Local Minima via First-Order Oracles NeurIPS 2018 NestedNet: Learning Nested Sparse Structures in Deep Neural Networks CVPR 2018 Net2Vec: Quantifying and Explaining How Concepts Are Encoded by Filters in Deep Neural Networks CVPR 2018 Network Approximation using Tensor Sketching IJCAI 2018 Neural Proximal Gradient Descent for Compressive Imaging NeurIPS 2018 Neural Speed Reading via Skim-RNN ICLR 2018 NISP: Pruning Networks Using Neuron Importance Score Propagation CVPR 2018 Norm matters: efficient and accurate normalization schemes in deep networks NeurIPS 2018 On Acceleration with Noise-Corrupted Gradients ICML 2018 Online Learning Rate Adaptation with Hypergradient Descent ICLR 2018 On Neuronal Capacity NeurIPS 2018 On the Convergence of Adam and Beyond ICLR 2018 On the Convergence Properties of a K-step Averaging Stochastic Gradient Descent Algorithm for Nonconvex Optimization IJCAI 2018 On the Generalization of Equivariance and Convolution in Neural Networks to the Action of Compact Groups ICML 2018 On the Global Convergence of Gradient Descent for Over-parameterized Models using Optimal Transport NeurIPS 2018 On the insufficiency of existing momentum schemes for Stochastic Optimization ICLR 2018 On the Local Minima of the Empirical Risk NeurIPS 2018 On the Practical Computational Power of Finite Precision RNNs for Language Recognition ACL 2018 On the Relative Expressiveness of Bayesian and Neural Networks PGM 2018 OpenNMT System Description for WNMT 2018: 800 words/sec on a single-core CPU ACL 2018 OpenSeq2Seq: Extensible Toolkit for Distributed and Mixed Precision Training of Sequence-to-Sequence Models ACL 2018 Optimization Algorithm Inspired Deep Neural Network Structure Design ACML 2018