Kevin Jamieson

Optimal Pricing for Bundles: Using Submodularity in Offline and Online Settings

Instance-Optimal Best-Arm Identification in Non-Stationary Linear Bandits

On the Universal Near Optimality of Hedge in Combinatorial Settings

Adapting to Stochastic and Adversarial Losses in Episodic MDPs with Aggregate Bandit Feedback

Learning to Incentivize in Repeated Principal-Agent Problems with Adversarial Agent Arrivals

Improved Regret Bounds for Linear Bandits with Heavy-Tailed Rewards