47 citations · 57 across the 13 of their papers we have counts for
8 papers · 1 filter
Confidence Estimation via Sequential Likelihood Mixing
Johannes Kirschner, Andreas Krause, Michele Meziu +1
We present a universal framework for constructing confidence sets based on sequential likelihood mixing. Building upon classical results from sequential analysis, we provide a unif…
Near-optimal Policy Identification in Active Reinforcement Learning
Xiang Li, Viraj Mehta, Johannes Kirschner +5
Many real-world reinforcement learning tasks require control of complex dynamical systems that involve both costly data acquisition processes and large state spaces. In cases where…
Bias-Robust Bayesian Optimization via Dueling Bandits
Johannes Kirschner, Andreas Krause
We consider Bayesian optimization in settings where observations can be adversarially biased, for example by an uncontrolled hidden confounder. Our first contribution is a reductio…
Efficient Pure Exploration for Combinatorial Bandits with Semi-Bandit Feedback
Marc Jourdan, Mojmír Mutný, Johannes Kirschner +1
Combinatorial bandits with semi-bandit feedback generalize multi-armed bandits, where the agent chooses sets of arms and observes a noisy reward for each arm contained in the chose…
Asymptotically Optimal Information-Directed Sampling
Johannes Kirschner, Tor Lattimore, Claire Vernade +1
We introduce a simple and efficient algorithm for stochastic linear bandits with finitely many actions that is asymptotically optimal and (nearly) worst-case optimal in finite time…
Distributionally Robust Bayesian Optimization
Johannes Kirschner, Ilija Bogunovic, Stefanie Jegelka +1
Robustness to distributional shift is one of the key challenges of contemporary machine learning. Attaining such robustness is the goal of distributionally robust optimization, whi…