Theory

Effectively Unbiased FID and Inception Score and Where to Find Them CVPR 2020 Efficient Proximal Mapping of the 1-path-norm of Shallow Networks ICML 2020 Empirical Bounds on Linear Regions of Deep Rectifier Networks AAAI 2020 Escaping Saddle-Point Faster under Interpolation-like Conditions NeurIPS 2020 Estimating Stochastic Linear Combination of Non-Linear Regressions AAAI 2020 Exactly Computing the Local Lipschitz Constant of ReLU Networks NeurIPS 2020 Fine-Grained Analysis of Stability and Generalization for Stochastic Gradient Descent ICML 2020 Finite Versus Infinite Neural Networks: an Empirical Study NeurIPS 2020 Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domains NeurIPS 2020 Generalization bound of globally optimal non-convex neural network training: Transportation map estimation by infinite dimensional Langevin dynamics NeurIPS 2020 Generalization Error Bounds of Gradient Descent for Learning Over-Parameterized Deep ReLU Networks AAAI 2020 Generalization error in high-dimensional perceptrons: Approaching Bayes error with convex optimization NeurIPS 2020 Good Subnetworks Provably Exist: Pruning via Greedy Forward Selection ICML 2020 Hierarchical nucleation in deep neural networks NeurIPS 2020 High-Frequency Component Helps Explain the Generalization of Convolutional Neural Networks CVPR 2020 Infinitely deep neural networks as diffusion processes AISTATS 2020 Information-Theoretic Local Minima Characterization and Regularization ICML 2020 Information-Theoretic Probing with Minimum Description Length EMNLP 2020 Information-Theoretic Understanding of Population Risk Improvement with Model Compression AAAI 2020 In search of robust measures of generalization NeurIPS 2020 Is the Skip Connection Provable to Reform the Neural Network Loss Landscape? IJCAI 2020 Kernelized information bottleneck leads to biologically plausible 3-factor Hebbian learning in deep networks NeurIPS 2020 Language Through a Prism: A Spectral Approach for Multiscale Language Representations NeurIPS 2020 Learning a Single Neuron with Gradient Methods COLT 2020 Learning Model with Error -- Exposing the Hidden Model of BAYHENN IJCAI 2020