Thompson sampling for prediction with expert advice
Mostra el registre complet Registre parcial de l'ítem
- dc.contributor.author Sánchez Pérez de Amézaga, Claudio
- dc.date.accessioned 2021-12-15T12:25:34Z
- dc.date.available 2021-12-15T12:25:34Z
- dc.date.issued 2021-09
- dc.description Treball fi de màster de: Master in Intelligent Interactive Systemsca
- dc.description Tutor: Gergely Neu
- dc.description.abstract We study Thompson Sampling for prediction with expert advice. With Follow the leader, and Follow the perturbed leader strategies, we present relevant results in order to proceed with Thompson Sampling Algorithm. Using a similar strategy used for studying Follow the perturbed leader, we decompose the regret in three terms. We study the expressions of choosing an expert from a set of experts. Here we show some interesting equivalences between the probability at time t, and the probability of a cheating forecaster which can see in the future t + 1. Finally, we present some experimental cases xing a nal time T. We analyze how the model selects the expert with the best performance. We obtain strong evidence to bound the diference between the cheating forecaster and the true one, following an exponential growth similar to T.ca
- dc.format.mimetype application/pdf*
- dc.identifier.uri http://hdl.handle.net/10230/49223
- dc.language.iso engca
- dc.rights Attribution-NonCommercial- NoDerivs 3.0 Spainca
- dc.rights.accessRights info:eu-repo/semantics/openAccessca
- dc.rights.uri https://creativecommons.org/licenses/by-nc-nd/3.0/es/ca
- dc.subject.other Algorismes
- dc.title Thompson sampling for prediction with expert adviceca
- dc.type info:eu-repo/semantics/masterThesisca