Theory

A Biresolution Spectral Framework for Product Quantization CVPR 2018 A Convex Duality Framework for GANs NeurIPS 2018 Analytic Expressions for Probabilistic Moments of PL-DNN With Gaussian Input CVPR 2018 An Empirical Evaluation of Sketched SVD and its Application to Leverage Score Ordering ACML 2018 Are ResNets Provably Better than Linear Predictors? NeurIPS 2018 A Theoretical Explanation for Perplexing Behaviors of Backpropagation-based Visualizations ICML 2018 Blind Deconvolutional Phase Retrieval via Convex Programming NeurIPS 2018 Bounds on the Approximation Power of Feedforward Neural Networks ICML 2018 Computing Higher Order Derivatives of Matrix and Tensor Expressions NeurIPS 2018 Convergence guarantees for a class of non-convex and non-smooth optimization problems ICML 2018 Deep Homogeneous Mixture Models: Representation, Separation, and Approximation NeurIPS 2018 DeepPINK: reproducible feature selection in deep neural networks NeurIPS 2018 Efficient Formal Safety Analysis of Neural Networks NeurIPS 2018 Fast generalization error bound of deep learning from a kernel perspective AISTATS 2018 Global Optimality Conditions for Deep Neural Networks ICLR 2018 Gradient Descent Learns One-hidden-layer CNN: Don’t be Afraid of Spurious Local Minima ICML 2018 Gradient Estimation with Simultaneous Perturbation and Compressive Sensing JMLR 2018 Hessian-based Analysis of Large Batch Training and Robustness to Adversaries NeurIPS 2018 How SGD Selects the Global Minima in Over-parameterized Learning: A Dynamical Stability Perspective NeurIPS 2018 How to Start Training: The Effect of Initialization and Architecture NeurIPS 2018 Implicit Bias of Gradient Descent on Linear Convolutional Networks NeurIPS 2018 Information-based Adaptive Stimulus Selection to Optimize Communication Efficiency in Brain-Computer Interfaces NeurIPS 2018 Learning Overparameterized Neural Networks via Stochastic Gradient Descent on Structured Data NeurIPS 2018 Local Identifiability of ℓ_1-minimization Dictionary Learning: a Sufficient and Almost Necessary Condition JMLR 2018 Meta-Learning and Universality: Deep Representations and Gradient Descent can Approximate any Learning Algorithm ICLR 2018