In many areas of Artificial Intelligence (AI), we are interested in helping people make better decisions. This help can result in two advantages. First, computers can process large amounts of data and perform quick calculations, leading to better decisions. Second, if a user does not have to think about some decisions, they have more time to focus on other things they find important. Since user...

We study a variant of the stochastic multi-armed bandit (MAB) problem in which the rewards are corrupted. In this framework, motivated by privacy preserving in online recommender systems, the goal is to maximize the sum of the (unobserved) rewards, based on the observation of transformation of these rewards through a stochastic corruption process with known parameters. We provide a lower bound ...

In this report, we will study online learning algorithms, and in particular, online mirror descent (OMD) method when applied to the collaborative filtering problem. This is motivated by the problem of real-world large-scale recommendation systems, where the goal is to make relevant recommendations to the users based on their demographic information, their past behavior, and the other users’ bah...

The unfavorable comparison between the obtained and expected outcomes of our choices may elicit disappointment. When the comparison is made with the outcome of alternative actions, emotions like regret can serve as a learning signal. Previous work showed that both anticipated disappointment and regret influence decisions. In addition, experienced regret is associated with higher emotional respo...

OBJECTIVES To identify patient-reported reasons for selecting obliterative surgery for the purpose of predicting decision regret and satisfaction. METHODS We created a deidentified database of patients who underwent an obliterative procedure for prolapse from 2006 to 2013. Patients were excluded if they declined study participation, were deceased, or had dementia. Participants completed a sur...

This paper investigates, for the first time in the literature, the approximation of min-max (regret) versions of classical problems like shortest path, minimum spanning tree, and knapsack. For a bounded number of scenarios, we establish fully polynomial-time approximation schemes for the min-max versions of these problems, using relationships between multi-objective and min-max optimization. Us...

In a partial monitoring game, the learner repeatedly chooses an action, the environment responds with an outcome, and then the learner suffers a loss and receives a feedback signal, both of which are fixed functions of the action and the outcome. The goal of the learner is to minimize his regret, which is the difference between his total cumulative loss and the total loss of the best fixed acti...

We introduce a natural extension of the notion of swap regret, conditional swap regret, that allows for action modifications conditioned on the player’s action history. We prove a series of new results for conditional swap regret minimization. We present algorithms for minimizing conditional swap regret with bounded conditioning history. We further extend these results to the case where conditi...