Theory

Weak Form Generalized Hamiltonian Learning NeurIPS 2020 What graph neural networks cannot learn: depth vs width ICLR 2020 What’s in a Name? Are BERT Named Entity Representations just as Good for any other Name? ACL 2020 When Do GNNs Work: Understanding and Improving Neighborhood Aggregation IJCAI 2020 When to Use Convolutional Neural Networks for Inverse Problems CVPR 2020 Why Do Deep Residual Networks Generalize Better than Deep Feedforward Networks? --- A Neural Tangent Kernel Perspective NeurIPS 2020 Wisdom of the Ensemble: Improving Consistency of Deep Learning Models NeurIPS 2020 Word Representations Concentrate and This is Good News! CoNLL 2020 Would you describe a leopard as yellow? Evaluating crowd-annotations with justified and informative disagreement COLING 2020 A Benchmark for Interpretability Methods in Deep Neural Networks NeurIPS 2019 Abstraction based Output Range Analysis for Neural Networks NeurIPS 2019 A Calibration Metric for Risk Scores with Survival Data MLHC 2019 Achieving Verified Robustness to Symbol Substitutions via Interval Bound Propagation EMNLP 2019 A Convergence Analysis of Gradient Descent for Deep Linear Neural Networks ICLR 2019 A Convergence Theory for Deep Learning via Over-Parameterization ICML 2019 Adaptive Estimators Show Information Compression in Deep Neural Networks ICLR 2019 Adaptive Influence Maximization with Myopic Feedback NeurIPS 2019 Adaptively Truncating Backpropagation Through Time to Control Gradient Bias UAI 2019 Adaptivity of deep ReLU network for learning in Besov and mixed smooth Besov spaces: optimal rate and curse of dimensionality ICLR 2019 A Domain Agnostic Measure for Monitoring and Evaluating GANs NeurIPS 2019 Adversarial Examples Are a Natural Consequence of Test Error in Noise ICML 2019 A General Theory of Equivariant CNNs on Homogeneous Spaces NeurIPS 2019 A Geometric Perspective on the Transferability of Adversarial Directions AISTATS 2019 A Kernel Multiple Change-point Algorithm via Model Selection JMLR 2019 A Kernel Perspective for Regularizing Deep Neural Networks ICML 2019