Theory

On the Global Optimality of Model-Agnostic Meta-Learning ICML 2020 On the Learnability of Possibilistic Theories IJCAI 2020 On the linearity of large non-linear models: when and why the tangent kernel is constant NeurIPS 2020 On the Max-Min Fair Stochastic Allocation of Indivisible Goods AAAI 2020 On the Number of Linear Regions of Convolutional Neural Networks ICML 2020 On the Optimal Weighted ℓ_2 Regularization in Overparameterized Linear Regression NeurIPS 2020 On the Regularization Properties of Structured Dropout CVPR 2020 On the Relationship between Self-Attention and Convolutional Layers ICLR 2020 On the Similarity between the Laplace and Neural Tangent Kernels NeurIPS 2020 On the Stability and Convergence of Robust Adversarial Reinforcement Learning: A Case Study on Linear Quadratic Systems NeurIPS 2020 On the Systematicity of Probing Contextualized Word Representations: The Case of Hypernymy in BERT COLING 2020 On the universality of deep learning NeurIPS 2020 On Uniform Convergence and Low-Norm Interpolation Learning NeurIPS 2020 On Universal Equivariant Set Networks ICLR 2020 Optimal Approximation - Smoothness Tradeoffs for Soft-Max Functions NeurIPS 2020 Optimal Continual Learning has Perfect Memory and is NP-hard ICML 2020 Optimal Group Testing COLT 2020 Optimally Deceiving a Learning Leader in Stackelberg Games NeurIPS 2020 Optimization Theory for ReLU Neural Networks Trained with Normalization Layers ICML 2020 Optimizing for the Future in Non-Stationary MDPs ICML 2020 Organizing recurrent network dynamics by task-computation to enable continual learning NeurIPS 2020 Over-parameterized Adversarial Training: An Analysis Overcoming the Curse of Dimensionality NeurIPS 2020 PAC-Bayes Analysis Beyond the Usual Bounds NeurIPS 2020 PAC-Bayesian Bound for the Conditional Value at Risk NeurIPS 2020 Parallels Between Phase Transitions and Circuit Complexity? COLT 2020