Theory

Modern Neural Networks Generalize on Small Data Sets NeurIPS 2018 NASH: Toward End-to-End Neural Architecture for Generative Semantic Hashing ACL 2018 On Neuronal Capacity NeurIPS 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 Practical Computational Power of Finite Precision RNNs for Language Recognition ACL 2018 Optimization Landscape and Expressivity of Deep CNNs ICML 2018 Parameters as interacting particles: long time convergence and asymptotic error scaling of neural networks NeurIPS 2018 Scaling provable adversarial defenses NeurIPS 2018 Self-Normalization Properties of Language Modeling COLING 2018 Smoothed analysis of the low-rank approach for smooth semidefinite programs NeurIPS 2018 Spectral Filtering for General Linear Dynamical Systems NeurIPS 2018 Stability and Generalization of Learning Algorithms that Converge to Global Optima ICML 2018 Stronger Generalization Bounds for Deep Nets via a Compression Approach ICML 2018 Structured Local Minima in Sparse Blind Deconvolution NeurIPS 2018 The emergence of spectral universality in deep networks AISTATS 2018 The Implicit Bias of Gradient Descent on Separable Data JMLR 2018 Theoretical Linear Convergence of Unfolded ISTA and Its Practical Weights and Thresholds NeurIPS 2018 The power of deeper networks for expressing natural functions ICLR 2018 The Spectrum of the Fisher Information Matrix of a Single-Hidden-Layer Neural Network NeurIPS 2018 Towards Provable Learning of Polynomial Neural Networks Using Low-Rank Matrix Estimation AISTATS 2018 Understanding Generalization and Optimization Performance of Deep CNNs ICML 2018 Understanding the Loss Surface of Neural Networks for Binary Classification ICML 2018 Visualizing the Loss Landscape of Neural Nets NeurIPS 2018 Which Neural Net Architectures Give Rise to Exploding and Vanishing Gradients? NeurIPS 2018