Learning Theory

Finding the Stochastic Shortest Path with Low Regret: the Adversarial Cost and Unknown Transition Case ICML 2021 Fine-Grained Gap-Dependent Bounds for Tabular MDPs via Adaptive Multi-Step Bootstrap COLT 2021 Fine-grained Generalization Analysis of Structured Output Prediction IJCAI 2021 Fine-grained Generalization Analysis of Vector-Valued Learning AAAI 2021 Finite Sample Analysis of Average-Reward TD Learning and Q-Learning NeurIPS 2021 Finite-sample Analysis of Interpolating Linear Classifiers in the Overparameterized Regime JMLR 2021 Finite-time System Identification and Adaptive Control in Autoregressive Exogenous Systems L4DC 2021 Fitting the Search Space of Weight-sharing NAS with Graph Convolutional Networks AAAI 2021 Formalizing Generalization and Adversarial Robustness of Neural Networks to Weight Perturbations NeurIPS 2021 For self-supervised learning, Rationality implies generalization, provably ICLR 2021 Forster Decomposition and Learning Halfspaces with Noise NeurIPS 2021 Fractal Structure and Generalization Properties of Stochastic Optimization Algorithms NeurIPS 2021 From Local Pseudorandom Generators to Hardness of Learning COLT 2021 Functions with average smoothness: structure, algorithms, and learning COLT 2021 Fundamental Limits of Ridge-Regularized Empirical Risk Minimization in High Dimensions AISTATS 2021 Gaussian Approximation for Bias Reduction in Q-Learning JMLR 2021 Generalization Bounds For Meta-Learning: An Information-Theoretic Analysis NeurIPS 2021 Generalization Bounds for Meta-Learning via PAC-Bayes and Uniform Stability NeurIPS 2021 Generalization Bounds for Stochastic Saddle Point Problems AISTATS 2021 Generalization Bounds for (Wasserstein) Robust Optimization NeurIPS 2021 Generalization Bounds in the Presence of Outliers: a Median-of-Means Study ICML 2021 Generalization bounds via distillation ICLR 2021 Generalization error bounds for deep unfolding RNNs UAI 2021 Generalization Error Rates in Kernel Regression: The Crossover from the Noiseless to Noisy Regime NeurIPS 2021 Generalization Guarantee of SGD for Pairwise Learning NeurIPS 2021