Learning Theory

Balanced Policy Evaluation and Learning NeurIPS 2018 Bandit Regret Scaling with the Effective Loss Range ALT 2018 Behavior Analysis of NLI Models: Uncovering the Influence of Three Factors on Robustness NAACL 2018 Benefits of over-parameterization with EM NeurIPS 2018 Best of both worlds: Stochastic & adversarial best-arm identification COLT 2018 Bias and Generalization in Deep Generative Models: An Empirical Study NeurIPS 2018 Bounding and Counting Linear Regions of Deep Neural Networks ICML 2018 Bounds on the Approximation Power of Feedforward Neural Networks ICML 2018 Breaking the 1/√n Barrier: Faster Rates for Permutation-based Models in Polynomial Time COLT 2018 But How Does It Work in Theory? Linear SVM with Random Features NeurIPS 2018 Butterfly Effects in Frame Semantic Parsing: impact of data processing on model ranking COLING 2018 Can recurrent neural networks warp time? ICLR 2018 Chaining Mutual Information and Tightening Generalization Bounds NeurIPS 2018 Combinatorial Pure Exploration with Continuous and Separable Reward Functions and Its Applications IJCAI 2018 Community Exploration: From Offline Optimization to Online Learning NeurIPS 2018 Constant Regret, Generalized Mixability, and Mirror Descent NeurIPS 2018 Context-dependent upper-confidence bounds for directed exploration NeurIPS 2018 Contextual Bandits with Stochastic Experts AISTATS 2018 Contextual bandits with surrogate losses: Margin bounds and efficient algorithms NeurIPS 2018 Contextual Pricing for Lipschitz Buyers NeurIPS 2018 Convergence Analysis of Gradient Descent for Eigenvector Computation IJCAI 2018 Convergence of Value Aggregation for Imitation Learning AISTATS 2018 Critical initialisation for deep signal propagation in noisy rectifier neural networks NeurIPS 2018 Curriculum Learning by Transfer Learning: Theory and Experiments with Deep Networks ICML 2018 Data-Driven Clustering via Parameterized Lloyd's Families NeurIPS 2018