Theory

RecurJac: An Efficient Recursive Algorithm for Bounding Jacobian Matrix of Neural Networks and Its Applications AAAI 2019 Regularization Matters: Generalization and Optimization of Neural Nets v.s. their Induced Kernel NeurIPS 2019 Relating RNN Layers with the Spectral WFA Ranks in Sequence Modelling ACL 2019 ResNet and Batch-normalization Improve Data Separability ACML 2019 Robust Attribution Regularization NeurIPS 2019 Robustness Verification of Classification Deep Neural Networks via Linear Programming CVPR 2019 Semi-flat minima and saddle points by embedding neural networks to overparameterization NeurIPS 2019 Sensitivity Analysis of Deep Neural Networks AAAI 2019 Sharp Restricted Isometry Bounds for the Inexistence of Spurious Local Minima in Nonconvex Matrix Recovery JMLR 2019 Spherical Regression: Learning Viewpoints, Surface Normals and 3D Rotations on N-Spheres CVPR 2019 Spurious Valleys in One-hidden-layer Neural Network Optimization Landscapes JMLR 2019 The Geometry of Deep Networks: Power Diagram Subdivision NeurIPS 2019 The Goldilocks Zone: Towards Better Understanding of Neural Network Loss Landscapes AAAI 2019 The Normalization Method for Alleviating Pathological Sharpness in Wide Neural Networks NeurIPS 2019 Theoretical Analysis of Auto Rate-Tuning by Batch Normalization ICLR 2019 Towards a Theoretical Understanding of Hashing-Based Neural Nets AISTATS 2019 Towards Understanding the Generalization Bias of Two Layer Convolutional Linear Classifiers with Gradient Descent AISTATS 2019 Transformer Dissection: An Unified Understanding for Transformer’s Attention via the Lens of Kernel EMNLP 2019 Trivializations for Gradient-Based Optimization on Manifolds NeurIPS 2019 Universal Approximation Property and Equivalence of Stochastic Computing-Based Neural Networks and Binary Neural Networks AAAI 2019 Unreproducible Research is Reproducible ICML 2019 Weisfeiler and Leman Go Neural: Higher-Order Graph Neural Networks AAAI 2019 What Can ResNet Learn Efficiently, Going Beyond Kernels? NeurIPS 2019 What is the Effect of Importance Weighting in Deep Learning? ICML 2019 Width Provably Matters in Optimization for Deep Linear Neural Networks ICML 2019