Search Results for author:
Found 7 papers, 3 papers with code
Anytime Model Selection in Linear Bandits
This allows us to develop ALEXP, which has an exponentially improved ($\log M$) dependence on $M$ for its regret.
Hallucinated Adversarial Control for Conservative Offline Policy Evaluation
We study the problem of conservative off-policy evaluation (COPE) where given an offline dataset of environment interactions, collected by other agents, we seek to obtain a (tight) lower bound on a policy's performance.
Instance-Dependent Generalization Bounds via Optimal Transport
Existing generalization bounds fail to explain crucial factors that drive the generalization of modern neural networks.
Lifelong Bandit Optimization: No Prior and No Regret
Our algorithm can be paired with any kernelized or linear bandit algorithm and guarantees oracle optimal performance, meaning that as more tasks are solved, the regret of LIBO on each task converges to the regret of the bandit algorithm with oracle knowledge of the true kernel.
Graph Neural Network Bandits
By establishing a novel connection between such kernels and the graph neural tangent kernel (GNTK), we introduce the first GNN confidence bound and use it to design a phased-elimination algorithm with sublinear regret.
Meta-Learning Hypothesis Spaces for Sequential Decision-making
We demonstrate our approach on the kernelized bandit problem (a. k. a.~Bayesian optimization), where we establish regret bounds competitive with those given the true kernel.
Neural Contextual Bandits without Regret
Contextual bandits are a rich model for sequential decision making given side information, with important applications, e. g., in recommender systems.
