arXiv research

Framework analyzes physical metrics in soccer to link performance with value.

We study a nonparametric contextual bandit problem where the expected reward functions belong to a Hölder class with smoothness parameter $β$. We show how this interpolates between two extremes that were previously studied in isolation: non-differentiable bandits ($β\leq1$), where rate-optimal regret is achieved by run…

Data that is gathered adaptively --- via bandit algorithms, for example --- exhibits bias. This is true both when gathering simple numeric valued data --- the empirical means kept track of by stochastic bandit algorithms are biased downwards --- and when gathering more complicated data --- running hypothesis tests on c…

In the classical contextual bandits problem, in each round $t$, a learner observes some context $c$, chooses some action $i$ to perform, and receives some reward $r_{i,t}(c)$. We consider the variant of this problem where in addition to receiving the reward $r_{i,t}(c)$, the learner also learns the values of $r_{i,t}(c…

Master algorithm selects best contextual bandit from a collection.

Contextual bandit algorithms have become popular for online recommendation systems such as Digg, Yahoo! Buzz, and news recommendation in general. \emph{Offline} evaluation of the effectiveness of new algorithms in these applications is critical for protecting online user experiences but very challenging due to their "p…

Paper introduces risk assessment for contextual bandits without experiments.

A new algorithm tackles graph-based contextual bandits with efficient regret bounds.

Paper develops robust OPF method using contextual information.

Study wSAA for contextual decisions, improving uncertainty quantification under computational constraints.

The paper provides bounds on the CDF of a variable under nonstationary conditions.

New algorithm reduces reinforcement learning complexity, approaching contextual bandits.

Much effort has been devoted to understanding the decisions of deep neural networks in recent years. A number of model-aware saliency methods were proposed to explain individual classification decisions by creating saliency maps. However, they are not applicable when the parameters and the gradients of the underlying m…

REN addresses uncertainty in user feedbacks for better recommendation systems.

New methods for anytime-valid off-policy inference in contextual bandits.

A new approach to hedging using contextual bandit models outperforms traditional methods.

OTSS learns personalized decision weights from logged decisions and outputs.

We address the problem of learning in an online setting where the learner repeatedly observes features, selects among a set of actions, and receives reward for the action taken. We provide the first efficient algorithm with an optimal regret. Our algorithm uses a cost sensitive classification learner as an oracle and h…

Jointly tackles assortment and pricing in retail, using bandit models.

New algorithm improves online learning under performance constraints.

Study online learning with off-policy feedback in adversarial bandit problems.

Contextualized ML learns context-dependent effects using deep learning.

IDS improves reinforcement learning with contextual information.

Algorithm optimizes bandit decisions with changing action sets using Gaussian processes.

Algorithm selects k arms from context-dependent options using Plackett-Luce model.

SADCBO optimizes contextual variables by balancing relevance and cost.

The bundle approach and n-contextuality reveal quantum model contextuality.

Optimizing an interactive system against a predefined online metric is particularly challenging, when the metric is computed from user feedback such as clicks and payments. The key challenge is the counterfactual nature: in the case of Web search, any change to a component of the search engine may result in a different…

Proposes a neural network for contextual regression.

Paper tackles domain adaptation for contextual bandits with sub-linear regret.

Transformers model contextual relations using probabilistic measures, revealing their expressive power.

Paper solves stochastic contextual linear bandits using linear bandit algorithms.

We study the problem of combining multiple bandit algorithms (that is, online learning algorithms with partial feedback) with the goal of creating a master algorithm that performs almost as well as the best base algorithm if it were to be run on its own. The main challenge is that when run with a master, base algorithm…

The study explores whether model selection guarantees apply to contextual bandits.

Faster algorithm reduces contextual bandit regret with fewer offline regression calls.

Efficiently handles contextual bandits with diffusion models.

This study analyzes how RNNs process context in sentiment analysis.

Thompson Sampling bounds for contextual bandits with sub-Gaussian rewards.

CADR estimator improves inference for contextual bandit data.

New algorithm learns optimal exploration parameters for contextual bandits.

The paper tackles learning varying DAG structures based on contextual features.

A method for unsupervised contextual anomaly detection is proposed using a cross-linked pair of Variational Auto-Encoders for assigning a normality score to an observation. The method enables a distinct separation of contextual from behavioral attributes and is robust to the presence of anomalous or novel contextual at…

A framework for auto-tuning hyper-parameters in contextual bandit algorithms.

New algorithm improves learning efficiency in multi-task contextual bandits.

We consider the stochastic linear (multi-armed) contextual bandit problem with the possibility of hidden simple multi-armed bandit structure in which the rewards are independent of the contextual information. Algorithms that are designed solely for one of the regimes are known to be sub-optimal for the alternate regime…

New algorithm for contextual dueling bandits achieves nearly optimal regret.

New algorithm reduces contextual bandits to efficient regression.

New method for contextual bandit with missing rewards.