Counterfactual Risk Minimization (CRM) is a framework for dealing with the logged bandit feedback problem, where the goal is to improve a logging policy using offline data. In this paper, we explore the case where it is possible to deploy learned policies multiple times and acquire new data. We extend the CRM principle and its theory to this scenario, which we call "Sequential Counterfactual Risk Minimization (SCRM)." We introduce a novel counterfactual estimator and identify conditions that can improve the performance of CRM in terms of excess risk and regret rates, by using an analysis similar to restart strategies in accelerated optimization methods. We also provide an empirical evaluation of our method in both discrete and continuous action settings, and demonstrate the benefits of multiple deployments of CRM.

In this paper, we tackle the computational efficiency of kernelized UCB algorithms in contextual bandits. While standard methods require a $\mathcal{O}(CT^3)$ complexity where $T$ is the horizon and the constant $C$ is related to optimizing the UCB rule, we propose an efficient contextual algorithm for large-scale problems. Specifically, our method relies on incremental Nyström approximations of the joint kernel embedding of contexts and actions. This allows us to achieve a complexity of $\mathcal{O}(CTm^2)$ where $m$ is the number of Nyström points. To recover the same regret as the standard kernelized UCB algorithm, $m$ needs to be of order of the effective dimension of the problem, which is at most $\mathcal{O}(\sqrt{T})$ and nearly constant in some cases.

In many online decision processes, the optimizing agent is called to choose between large numbers of alternatives with many inherent similarities; in turn, these similarities imply closely correlated losses that may confound standard discrete choice models and bandit algorithms. We study this question in the context of nested bandits, a class of adversarial multi-armed bandit problems where the learner seeks to minimize their regret in the presence of a large number of distinct alternatives with a hierarchy of embedded (non-combinatorial) similarities. In this setting, optimal algorithms based on the exponential weights blueprint (like Hedge, EXP3, and their variants) may incur significant regret because they tend to spend excessive amounts of time exploring irrelevant alternatives with similar, suboptimal costs. To account for this, we propose a nested exponential weights (NEW) algorithm that performs a layered exploration of the learner’s set of alternatives based on a nested, step-by-step selection method. In so doing, we obtain a series of tight bounds for the learner’s regret showing that online learning problems with a high degree of similarity between alternatives can be resolved efficiently, without a red bus / blue bus paradox occurring.

We propose a hierarchical version of dual averaging for zeroth-order online non-convex optimization {–} i.e., learning processes where, at each stage, the optimizer is facing an unknown non-convex loss function and only receives the incurred loss as feedback. The proposed class of policies relies on the construction of an online model that aggregates loss information as it arrives, and it consists of two principal components: (a) a regularizer adapted to the Fisher information metric (as opposed to the metric norm of the ambient space); and (b) a principled exploration of the problem’s state space based on an adapted hierarchical schedule. This construction enables sharper control of the model’s bias and variance, and allows us to derive tight bounds for both the learner’s static and dynamic regret {–} i.e., the regret incurred against the best dynamic policy in hindsight over the horizon of play.

Individual Treatment Effect (ITE) estimation is an extensively researched problem, with applications in various domains. We model the case where there exists heterogeneous non-compliance to a randomly assigned treatment, a typical situation in health (because of non-compliance to prescription) or digital advertising (because of competition and ad blockers for instance). The lower the compliance, the more the effect of treatment prescription - or individual prescription effect (IPE) - signal fades away and becomes harder to estimate. We propose a new approach for the estimation of the IPE that takes advantage of observed compliance information to prevent signal fading. Using the Structural Causal Model framework and do-calculus, we define a general mediated causal effect setting and propose a corresponding estimator which consistently recovers the IPE with asymptotic variance guarantees. Finally, we conduct experiments on both synthetic and real-world datasets that highlight the benefit of the approach, which consistently improves state-of-the-art in low compliance settings.

We consider the problem of online learning with non-convex losses. In terms of feedback, we assume that the learner observes – or otherwise constructs – an inexact model for the loss function encountered at each stage, and we propose a mixed-strategy learning policy based on dual averaging. In this general context, we derive a series of tight regret minimization guarantees, both for the learner’s static (external) regret, as well as the regret incurred against the best dynamic policy in hindsight. Subsequently, we apply this general template to the case where the learner only has access to the actual loss incurred at each stage of the process. This is achieved by means of a kernel-based estimator which generates an inexact model for each round’s loss function using only the learner’s realized losses as input.

This paper addresses the detection of emboli from signals acquired with a new miniaturized and portable transcranial Doppler ultrasound device. The use of this device enables outpatient monitoring but increases the number of artifacts. These artifacts usually come from the patient voice and motion and can be superimposed to emboli. For this reason and because of the scarcity of emboli compared to artifacts, reliably detect emboli is a challenging task. As an example, the 11809 s of signal used in this study contained 0.06 % of embolic events and 10.14 % of artifacts. Herein, we propose an automatic and sequential approach. The method is based on sequential determination of high intensity transient signals. We also define efficient features to describe emboli in the time frequency representation. On our database, the number of artifacts detected as emboli is divided by more than 10 compared to the other algorithms reported in the literature.

We carry out a systematic study of existing visual CAPTCHAs based on distorted characters that are augmented with anti-segmentation techniques. Applying a systematic evaluation methodology to 15 current CAPTCHA schemes from popular web sites, we find that 13 are vulnerable to automated attacks. Based on this evaluation, we identify a series of recommendations for CAPTCHA designers and attackers, and possible future directions for producing more reliable human/computer distinguishers.