Theory

On the Behavior of Intrinsically High-Dimensional Spaces: Distances, Direct and Reverse Nearest Neighbors, and Hubness JMLR 2018 On the Convergence of PatchMatch and Its Variants CVPR 2018 On the Convergence Properties of a K-step Averaging Stochastic Gradient Descent Algorithm for Nonconvex Optimization IJCAI 2018 On the Dimensionality of Word Embedding NeurIPS 2018 On the Discrimination-Generalization Tradeoff in GANs ICLR 2018 On the Expressive Power of Overlapping Architectures of Deep Learning ICLR 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 importance of single directions for generalization ICLR 2018 On the Information Bottleneck Theory of Deep Learning ICLR 2018 On the Limitations of First-Order Approximation in GAN Dynamics ICML 2018 On the Local Minima of the Empirical Risk NeurIPS 2018 On the Logical Properties of the Description Logic DL^N (Extended abstract) IJCAI 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 On the Spectrum of Random Features Maps of High Dimensional Data ICML 2018 On the State of the Art of Evaluation in Neural Language Models ICLR 2018 Open Category Detection with PAC Guarantees ICML 2018 Optimal approximation of continuous functions by very deep ReLU networks COLT 2018 Optimal Bounds for Johnson-Lindenstrauss Transformations JMLR 2018 Optimal Cooperative Inference AISTATS 2018 Optimal Errors and Phase Transitions in High-Dimensional Generalized Linear Models COLT 2018 Out-of-Distribution Detection using Multiple Semantic Label Representations NeurIPS 2018 Overfitting or perfect fitting? Risk bounds for classification and regression rules that interpolate NeurIPS 2018 PAC-Bayes bounds for stable algorithms with instance-dependent priors NeurIPS 2018