Postdoctoral Researcher
Department of Electrical Engineering and Computer Sciences
UC Berkeley
I am a postdoctoral researcher at UC Berkeley, hosted by Michael I. Jordan. Previously, I was a PhD student at ETH Zurich in Florian Dörfler's research group. My research focuses on decision-making under uncertainty, with a particular emphasis on the tension between robustness and adaptivity: how can decisions remain reliable under uncertainty without being more conservative than the available information warrants? I address this tension by using data and problem structure to characterize decision-relevant uncertainty, and by developing methods and algorithms that adapt as information accumulates. My research spans three interconnected directions:
Adaptive and self-certifying stochastic optimization: Can a stochastic optimization algorithm certify its own progress, adapt in real time, and decide when to stop?
Optimization under structured uncertainty: How should we model uncertainty involving rare events, temporal dynamics, or graph topology, and how should optimization exploit that structure?
Uncertainty quantification for machine learning: Can machine learning models provide statistically valid guarantees about the uncertainty associated with their predictions?