5 papers
Sequential Choice Bandits with Feedback for Personalizing users' experience
Anshuka Rangi, Massimo Franceschetti, Long Tran-Thanh
In this work, we study sequential choice bandits with feedback. We propose bandit algorithms for a platform that personalizes users' experience to maximize its rewards. For each ac…
Non-Stochastic Information Theory
Anshuka Rangi, Massimo Franceschetti
In an effort to develop the foundations for a non-stochastic theory of information, the notion of -mutual information between uncertain variables is introduced as a generalizati…
Unifying the stochastic and the adversarial Bandits with Knapsack
Anshuka Rangi, Massimo Franceschetti, Long Tran-Thanh
This paper investigates the adversarial Bandits with Knapsack (BwK) online learning problem, where a player repeatedly chooses to perform an action, pays the corresponding cost, an…
Online learning with feedback graphs and switching costs
Anshuka Rangi, Massimo Franceschetti
We study online learning when partial feedback information is provided following every action of the learning process, and the learner incurs switching costs for changing his actio…
Distributed Chernoff Test: Optimal decision systems over networks
Anshuka Rangi, Massimo Franceschetti, Stefano Marano
We study "active" decision making over sensor networks where the sensors' sequential probing actions are actively chosen by continuously learning from past observations. We conside…