We design differentially private algorithms for the problem of online linear optimization in the full information and bandit settings with optimal Õ( √ T )1 regret bounds. In the full-information setting, our results demonstrate that ε-differential privacy may be ensured for free – in particular, the regret bounds scale as O( √ T ) + Õ ( 1 ε ) . For bandit linear optimization, and as a special ...

Prior research on regret has assumed a consideration set of only two-alternatives. The authors have relaxed that assumption and have developed hypotheses to examine the influence of the unawareness set and order effects in the measurement of consumer regret in a post-purchase evaluation. The results demonstrated that the brands consumers were previously unaware of, do indeed influence consumer ...

Various papers have analyzed the noisy optimization of convex functions. This analysis has been made according to several criteria used to evaluate the performance of algorithms: uniform rate, simple regret and cumulative regret. We propose an iterative optimization framework, a particular instance of which, using Hessian approximations, provably (i) reaches the same rate as Kiefer-Wolfowitz al...

In this paper, we investigate the online non-convex optimization problem which generalizes the classic online convex optimization problem by relaxing the convexity assumption on the cost function. For this type of problem, the classic exponential weighting online algorithm has recently been shown to attain a sub-linear regret of O( √ T log T ). In this paper, we introduce a novel recursive stru...

Using data obtained in a controlled ad-auction experiment that we ran, we evaluate the regret-based approach to econometrics that was recently suggested by Nekipelov, Syrgkanis, and Tardos (EC 2015). We found that despite the weak regret-based assumptions, the results were (at least) as accurate as those obtained using classical equilibrium-based assumptions. En route we studied to what extent ...

Often, preferences are driven by comparisons with choices not made. Preferences of a decision-maker over a set of options may arise from regret, i.e., from comparisons with alternatives forgone by the decision maker. This is natural when the decision maker has to choose between two options with random outcomes. Once the uncertainty is resolved he will know what outcome he received, but also wha...

Purpose – The primary purpose of this research was to investigate the role of anticipated regret in time-based work-family conflict decisions. Design/methodology/approach – A total of 90 working parents responded to a decision making problem describing a time-based conflict between a work event and a family event. Participants’ preference for which event to attend constituted the dependent vari...

We propose that decision maker's regulatory mode affects risk-taking through anticipated regret. In the Study 1 either a locomotion or an assessment orientation were experimentally induced, and in the Studies 2 and 3 these different orientations were assessed as chronic individual differences. To assess risk-taking we used two behavioral measures of risk: BART and hot-CCT. The results show that...

A regret minimizing set Q is a small size representation of a much larger database P so that user queries executed on Q return answers whose scores are not much worse than those on the full dataset. In particular, a k-regret minimizing set has the property that the regret ratio between the score of the top-1 item in Q and the score of the top-k item in P is minimized, where the score of an item...

We consider a variation on the problem of prediction with expert advice, where new forecasters that were unknown until then may appear at each round. As often in prediction with expert advice, designing an algorithm that achieves near-optimal regret guarantees is straightforward, using aggregation of experts. However, when the comparison class is sufficiently rich, for instance when the best ex...