Theory

A Formal Hierarchy of RNN Architectures ACL 2020 Analytic Characterization of the Hessian in Shallow ReLU Models: A Tale of Symmetry NeurIPS 2020 An information theoretic view on selecting linguistic probes EMNLP 2020 An Internal Covariate Shift Bounding Algorithm for Deep Neural Networks by Unitizing Layers' Outputs CVPR 2020 Are Transformers universal approximators of sequence-to-sequence functions? ICLR 2020 A shooting formulation of deep learning NeurIPS 2020 Assessing Local Generalization Capability in Deep Models AISTATS 2020 Associative Memory in Iterated Overparameterized Sigmoid Autoencoders ICML 2020 Asymptotic normality and confidence intervals for derivatives of 2-layers neural network in the random features model NeurIPS 2020 Asymptotics of Wide Networks from Feynman Diagrams ICLR 2020 Attribution in Scale and Space CVPR 2020 Batch normalization provably avoids ranks collapse for randomly initialised deep networks NeurIPS 2020 Byte Pair Encoding is Suboptimal for Language Model Pretraining EMNLP 2020 Can Implicit Bias Explain Generalization? Stochastic Convex Optimization as a Case Study NeurIPS 2020 Certified Defense to Image Transformations via Randomized Smoothing NeurIPS 2020 Chaining Meets Chain Rule: Multilevel Entropic Regularization and Training of Neural Networks JMLR 2020 Collegial Ensembles NeurIPS 2020 Counterexample-Guided Learning of Monotonic Neural Networks NeurIPS 2020 Dataless Model Selection With the Deep Frame Potential CVPR 2020 Deep learning versus kernel learning: an empirical study of loss landscape geometry and the time evolution of the Neural Tangent Kernel NeurIPS 2020 Directional convergence and alignment in deep learning NeurIPS 2020 DNNs as Layers of Cooperating Classifiers AAAI 2020 Dynamical mean-field theory for stochastic gradient descent in Gaussian mixture classification NeurIPS 2020 Dynamical System Inspired Adaptive Time Stepping Controller for Residual Network Families AAAI 2020 Dynamics of Deep Neural Networks and Neural Tangent Hierarchy ICML 2020