This work investigates the offline formulation of the contextual bandit problem, where the goal is to leverage past interactions collected under a behavior policy to evaluate, select, and learn new, potentially better-performing, policies. Motivated by critical applications, we move beyond point estimators. Instead, we adopt the principle of _pessimism_ where we construct upper bounds that assess a policy's worst-case performance, enabling us to confidently select and learn improved policies. Precisely, we introduce novel, fully empirical concentration bounds for a broad class of importance weighting risk estimators. These bounds are general enough to cover most existing estimators and pave the way for the development of new ones. In particular, our pursuit of the tightest bound within this class motivates a novel estimator (LS), that _logarithmically smoothes_ large importance weights. The bound for LS is provably tighter than its competitors, and naturally results in improved policy selection and learning strategies. Extensive policy evaluation, selection, and learning experiments highlight the versatility and favorable performance of LS.

Personalised interactive systems such as recommender systems require selecting relevant items from massive catalogs dependent on context. Reward-driven offline optimisation of these systems can be achieved by a relaxation of the discrete problem resulting in policy learning or REINFORCE style learning algorithms. Unfortunately, this relaxation step requires computing a sum over the entire catalogue making the complexity of the evaluation of the gradient (and hence each stochastic gradient descent iterations) linear in the catalogue size. This calculation is untenable in many real world examples such as large catalogue recommender systems, severely limiting the usefulness of this method in practice. In this paper, we derive an approximation of these policy learning algorithms that scale logarithmically with the catalogue size. Our contribution is based upon combining three novel ideas: a new Monte Carlo estimate of the gradient of a policy, the self normalised importance sampling estimator and the use of fast maximum inner product search at training time. Extensive experiments show that our algorithm is an order of magnitude faster than naive approaches yet produces equally good policies.

This paper introduces a new principled approach for off-policy learning in contextual bandits. Unlike previous work, our approach does not derive learning principles from intractable or loose bounds. We analyse the problem through the PAC-Bayesian lens, interpreting policies as mixtures of decision rules. This allows us to propose novel generalization bounds and provide tractable algorithms to optimize them. We prove that the derived bounds are tighter than their competitors, and can be optimized directly to confidently improve upon the logging policy offline. Our approach learns policies with guarantees, uses all available data and does not require tuning additional hyperparameters on held-out sets. We demonstrate through extensive experiments the effectiveness of our approach in providing performance guarantees in practical scenarios.

How can we build and optimize a recommender system that must rapidly fill slates (i.e. banners) of personalized recommendations? The combination of deep learning stacks with fast maximum inner product search (MIPS) algorithms have shown it is possible to deploy flexible models in production that can rapidly deliver personalized recommendations to users. Albeit promising, this methodology is unfortunately not sufficient to build a recommender system which maximizes the reward, e.g. the probability of click. Usually instead a proxy loss is optimized and A/B testing is used to test if the system actually improved performance. This tutorial takes participants through the necessary steps to model the reward and directly optimize the reward of recommendation engines built upon fast search algorithms to produce high-performance reward-optimizing recommender systems.

A common task for recommender systems is to build a profile of the interests of a user from items in their browsing history and later to recommend items to the user from the same catalog. The users' behavior consists of two parts: the sequence of items that they viewed without intervention (the organic part) and the sequences of items recommended to them and their outcome (the bandit part).

We develop the value based approach to Recommender systems. The value approach is a model based approach that allows forecasting of actual A/B test performance. It contrasts with the proxy based approach, which attempt to order the performance of different recommendation systems, but not forecast actual performance. It also contrasts with policy based approaches which also produce a performance forecast but use propensity scores to by-pass the requirement for a model. Value based approaches are a state of the art approach for combining organic and bandit signals that can utilise the three fundamental distances of recommendation. Their deployment requires sophisticated modelling and Bayesian computation. This tutorial develops the theory of value based recommendation and demonstrates the approach with examples in python notebooks.