Print Email Facebook Twitter Online Convex Optimization with Predictions Title Online Convex Optimization with Predictions: Static and Dynamic Environments Author Zattoni Scroccaro, Pedro (TU Delft Mechanical, Maritime and Materials Engineering; TU Delft Delft Center for Systems and Control) Contributor Mohajerin Esfahani, P. (mentor) Grammatico, S. (graduation committee) Atasoy, B. (graduation committee) Sharifi Kolarijani, A. (graduation committee) Degree granting institution Delft University of Technology Programme Mechanical Engineering | Systems and Control Date 2020-09-21 Abstract In this thesis, we study Online Convex Optimization algorithms that exploit predictive and/or dynamical information about a problem instance. These features are inspired by recent developments in the Online Mirror Decent literature. When the Player's performance is compared with the best fixed decision in hindsight, we show that it is possible to achieve constant regret bounds under perfect gradient predictions and optimal minimax bounds in the worst-case, generalizing previous results from the literature. For dynamic environments, we propose a new algorithm, and show that it achieves dynamic regret bounds that exploit both gradient predictions and knowledge about the dynamics of the action sequence that the Player's performance is being compared with. We present results for both convex and strongly convex costs. Finally, we provide numerical experiments that corroborate our theoretical results. Subject Online Convex OptimizationPredictionOnline Learning To reference this document use: http://resolver.tudelft.nl/uuid:ce13b0da-fb0a-4e9f-b5a4-ef9b0dadf29b Part of collection Student theses Document type master thesis Rights © 2020 Pedro Zattoni Scroccaro Files PDF master_thesis_Pedro_Zatto ... occaro.pdf 2.21 MB Close viewer /islandora/object/uuid:ce13b0da-fb0a-4e9f-b5a4-ef9b0dadf29b/datastream/OBJ/view