Learning Theory

On Overfitting and Asymptotic Bias in Batch Reinforcement Learning with Partial Observability (Extended Abstract) IJCAI 2020 On Performance Estimation in Automatic Algorithm Configuration AAAI 2020 On ranking via sorting by estimated expected utility NeurIPS 2020 On Regret with Multiple Best Arms NeurIPS 2020 On Suboptimality of Least Squares with Application to Estimation of Convex Bodies COLT 2020 On the Ability and Limitations of Transformers to Recognize Formal Languages EMNLP 2020 On the Branching Bias of Syntax Extracted from Pre-trained Language Models EMNLP 2020 On the Complexity of Proper Distribution-Free Learning of Linear Classifiers ALT 2020 On the distance between two neural networks and the stability of learning NeurIPS 2020 On the Equivalence between Online and Private Learnability beyond Binary Classification NeurIPS 2020 On the Global Convergence Rates of Softmax Policy Gradient Methods ICML 2020 On the Interplay Between Fine-tuning and Sentence-Level Probing for Linguistic Knowledge in Pre-Trained Transformers EMNLP 2020 On the interplay between noise and curvature and its effect on optimization and generalization AISTATS 2020 On the Learnability of Possibilistic Theories IJCAI 2020 On the limits of cross-domain generalization in automated X-ray prediction MIDL 2020 On the Modularity of Hypernetworks NeurIPS 2020 On the Multiple Descent of Minimum-Norm Interpolants and Restricted Lower Isometry of Kernels COLT 2020 On the Practical Ability of Recurrent Neural Networks to Recognize Hierarchical Languages COLING 2020 On the Sample Complexity of Adversarial Multi-Source PAC Learning ICML 2020 On the Sample Complexity of Learning Sum-Product Networks AISTATS 2020 On the Theory of Transfer Learning: The Importance of Task Diversity NeurIPS 2020 On the universality of deep learning NeurIPS 2020 On the Value of Out-of-Distribution Testing: An Example of Goodhart's Law NeurIPS 2020 On Thompson Sampling for Smoother-than-Lipschitz Bandits AISTATS 2020 On Uniform Convergence and Low-Norm Interpolation Learning NeurIPS 2020