arXiv research

New algorithm minimizes expert selection regret in partial bandit feedback.

We use online convex optimization (OCO) for setpoint tracking with uncertain, flexible loads. We consider full feedback from the loads, bandit feedback, and two intermediate types of feedback: partial bandit where a subset of the loads are individually observed and the rest are observed in aggregate, and Bernoulli feed…

Estimates mode from partial feedback, improving AI learning pipelines.

Paper studies CLO with partial feedback, improving decision-making in uncertain contexts.

We propose a generalization of the best arm identification problem in stochastic multi-armed bandits (MAB) to the setting where every pull of an arm is associated with delayed feedback. The delay in feedback increases the effective sample complexity of standard algorithms, but can be offset if we have access to partial…

The paper tackles combinatorial pure exploration with various feedback structures and proposes efficient algorithms.

We study the adversarial multi-armed bandit problem where partial observations are available and where, in addition to the loss incurred for each action, a \emph{switching cost} is incurred for shifting to a new action. All previously known results incur a factor proportional to the independence number of the feedback …

Reduces user feedback needed for accurate recommender systems.

Unified framework for expert selection with bandit and lower-bound feedback.

New algorithms for efficient learning with partial information, reducing regret.

Bandit structured prediction describes a stochastic optimization framework where learning is performed from partial feedback. This feedback is received in the form of a task loss evaluation to a predicted output structure, without having access to gold standard structures. We advance this framework by lifting linear ba…

Stochastic structured prediction under bandit feedback follows a learning protocol where on each of a sequence of iterations, the learner receives an input, predicts an output structure, and receives partial feedback in form of a task loss evaluation of the predicted structure. We present applications of this learning …

New algorithm for multi-armed bandits with delayed, partially observed rewards.

Paper tackles dueling bandits with delayed feedback, revealing preference bias.

IDS algorithm optimizes sequential decisions in various monitoring settings.

We investigate contextual online learning with nonparametric (Lipschitz) comparison classes under different assumptions on losses and feedback information. For full information feedback and Lipschitz losses, we design the first explicit algorithm achieving the minimax regret rate (up to log factors). In a partial feedb…

Proposes online conformal prediction method with adversarial semi-bandit feedback.

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

Adaptive MAB algorithms handle composite, anonymous feedback without reward interval knowledge.

New method reduces bias in learning from large action spaces using selective importance sampling.

Stochastic linear bandits are a natural and well-studied model for structured exploration/exploitation problems and are widely used in applications such as online marketing and recommendation. One of the main challenges faced by practitioners hoping to apply existing algorithms is that usually the feedback is randomly …

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…

Algorithm learns NE in imperfect information games with imperfect feedback.

We present and study a partial-information model of online learning, where a decision maker repeatedly chooses from a finite set of actions, and observes some subset of the associated losses. This naturally models several situations where the losses of different actions are related, and knowing the loss of one action p…

Study optimal arms in combinatorial bandits with semi-bandit feedback and finite budget.

Paper tackles noisy bandit feedback for multiclass classification.

Study online multiclass classification under bandit feedback, extending previous results.

New Thompson sampling algorithm for stochastic partial monitoring achieves logarithmic regret.

New method uses correlated auxiliary feedback to reduce regret in parameterized bandits.

Algorithm provides online learning guarantees against general comparators in full and bandit feedback.

Banker-OMD improves online learning with delayed feedback.

Paper tackles stochastic $k$-submodular bandits with full feedback, achieving sublinear regret.

New framework tackles submodular welfare with multi-agent combinatorial bandits.

One-bit feedback suffices for a bandit problem's optimal strategy.

New algorithms handle online prediction with bandit and delayed feedback, improving regret bounds.

Efficient boosting method for regression with limited feedback.

New algorithm reduces regret in delayed feedback generalised linear bandits.

Neural algorithms optimize arm selection with human preference feedback for complex reward functions.

New algorithms ensure fair selection in combinatorial semi-bandit with unrestricted delays.

New algorithms tackle adversarial combinatorial bandits with switching costs.

We present a study on reinforcement learning (RL) from human bandit feedback for sequence-to-sequence learning, exemplified by the task of bandit neural machine translation (NMT). We investigate the reliability of human bandit feedback, and analyze the influence of reliability on the learnability of a reward estimator,…

We consider the problem of online combinatorial optimization under semi-bandit feedback, where a learner has to repeatedly pick actions from a combinatorial decision set in order to minimize the total losses associated with its decisions. After making each decision, the learner observes the losses associated with its a…

We consider a partial-feedback variant of the well-studied online PCA problem where a learner attempts to predict a sequence of $d$-dimensional vectors in terms of a quadratic loss, while only having limited feedback about the environment's choices. We focus on a natural notion of bandit feedback where the learner only…

We present online boosting algorithms for multiclass classification with bandit feedback, where the learner only receives feedback about the correctness of its prediction. We propose an unbiased estimate of the loss using a randomized prediction, allowing the model to update its weak learners with limited information. …

Multi-armed bandit(MAB) problem is a reinforcement learning framework where an agent tries to maximise her profit by proper selection of actions through absolute feedback for each action. The dueling bandits problem is a variation of MAB problem in which an agent chooses a pair of actions and receives relative feedback…

Algorithm allocates budgets to tasks with semi-bandit feedback, achieving near-optimal regret bounds.

A new algorithm for conversational recommendation systems using dueling bandits in GLMs.

New algorithm controls linear systems with bandit feedback, achieving optimal regret.