Dissertation Defense: Learning-based Decision-making under Stochastic and Adversarial Uncertainties

Abridged Abstract:

This thesis studies two online learning problems in which the efficiency of the proposed strategies is studied in terms of their regret. The first problem works on finding an asymptotically optimal strategy for prediction with expert advice and the second one involves designing learning algorithms that optimize the social welfare of a single server queuing system when both the arrival and service rates are unknown.

Hybrid Defense:
East Hall 4088
https://umich.zoom.us/j/98700417559
Passcode: 647236