Theory

On Dynamic Programming Decompositions of Static Risk Measures in Markov Decision Processes NeurIPS 2023 On Enhancing Expressive Power via Compositions of Single Fixed-Size ReLU Network ICML 2023 One Policy is Enough: Parallel Exploration with a Single Policy is Near-Optimal for Reward-Free Reinforcement Learning AISTATS 2023 On Error and Compression Rates for Prototype Rules AAAI 2023 One-step differentiation of iterative algorithms NeurIPS 2023 On Learning Latent Models with Multi-Instance Weak Supervision NeurIPS 2023 Online Control for Meta-optimization NeurIPS 2023 Online Estimation of the Koopman Operator Using Fourier Features L4DC 2023 Online Mechanism Design for Information Acquisition ICML 2023 Online PCA in Converging Self-consistent Field Equations NeurIPS 2023 Online Reinforcement Learning with Uncertain Episode Lengths AAAI 2023 Online RL in Linearly q^π-Realizable MDPs Is as Easy as in Linear MDPs If You Learn What to Ignore NeurIPS 2023 On Minimizing the Impact of Dataset Shifts on Actionable Explanations UAI 2023 On permutation symmetries in Bayesian neural network posteriors: a variational perspective NeurIPS 2023 On Proper Learnability between Average- and Worst-case Robustness NeurIPS 2023 On Robust Streaming for Learning with Experts: Algorithms and Lower Bounds NeurIPS 2023 On skip connections and normalisation layers in deep optimisation NeurIPS 2023 On Testability and Goodness of Fit Tests in Missing Data Models UAI 2023 On the Asymptotic Learning Curves of Kernel Ridge Regression under Power-law Decay NeurIPS 2023 On the bias of K-fold cross validation with stable learners AISTATS 2023 On the Compilability of Bounded Numeric Planning IJCAI 2023 On the Complexity of Counterfactual Reasoning IJCAI 2023 On the Complexity of SHAP-Score-Based Explanations: Tractability via Knowledge Compilation and Non-Approximability Results JMLR 2023 On The Computational Complexity of Self-Attention ALT 2023 On the Connection Between MPNN and Graph Transformer ICML 2023