Dear all,
This Monday, October 21, we have Julien Zhou speaking in the
Statistics and Machine Learning Thematic Seminar. Julien is a
visiting PhD student from Inria and Criteo.
Julien Zhou (Inria Grenoble-Alpes and Criteo AI Lab,
https://jlnzhou.github.io/)
Monday October 21, 16h00-17h00
Hybrid, at the University of Amsterdam and Online
Location: Korteweg-de Vries Institute for Mathematics, Science Park
907, Room F1.15
Directions: https://kdvi.uva.nl/contact/contact.html
Online: https://uva-live.zoom.us/j/83485037604
Submodular Optimization with Bandit feedbacks
We address the online unconstrained submodular maximization
problem (Online USM), in a setting with stochastic bandit feedback.
In this framework, a decision-maker receives noisy rewards from a
nonmonotone submodular function, taking values in a known bounded
interval. We propose an Explore-then-Commit inspired approach
satisfying logarithmic problem-dependent, 1/2-approximate regret,
leveraging the inner structure of the reward.
Seminar organizers:
Tim van Erven
https://mschauer.github.io/StructuresSeminar/
--
Tim van Erven <tim@timvanerven.nl>
www.timvanerven.nl