arXiv research

BLOB combines organic and bandit signals for better user interest estimation.

New algorithm for partially observable contexts in finance.

New action poisoning attacks improve LinUCB's performance by changing action signals.

Paper tackles federated linear bandit learning with AirComp for noisy channels.

Study bandit problems with BMO functions, achieving poly-log $δ$-regret.

New algorithm learns optimal decisions from imperfectly observed contexts.

We study adversarial attacks that manipulate the reward signals to control the actions chosen by a stochastic multi-armed bandit algorithm. We propose the first attack against two popular bandit algorithms: $ε$-greedy and UCB, \emph{without} knowledge of the mean rewards. The attacker is able to spend only logarithmic …

New framework uses user feedback in CB problems for better decision-making.

We investigate the feasibility of learning from a mix of both fully-labeled supervised data and contextual bandit data. We specifically consider settings in which the underlying learning signal may be different between these two data sources. Theoretically, we state and prove no-regret algorithms for learning that is r…

Study tests feasibility of linear programs with bandit feedback.

This paper analyzes the multi-armed bandit problem using frequency-domain methods.

New method clusters items with bandit feedback without parametric assumptions.

We describe MELEE, a meta-learning algorithm for learning a good exploration policy in the interactive contextual bandit setting. Here, an algorithm must take actions based on contexts, and learn based only on a reward signal from the action taken, thereby generating an exploration/exploitation trade-off. MELEE address…

This paper tackles fair online decision-making in contextual bandits, achieving optimal performance and fairness.

We formulate the problem of sampling and recovering clustered graph signal as a multi-armed bandit (MAB) problem. This formulation lends naturally to learning sampling strategies using the well-known gradient MAB algorithm. In particular, the sampling strategy is represented as a probability distribution over the indiv…

DG improves policy gradient efficiency by selectively backpropagating only valuable samples.

New bounds for high-dimensional sparse linear bandits, balancing information and regret.

Multi-armed bandit problems are receiving a great deal of attention because they adequately formalize the exploration-exploitation trade-offs arising in several industrially relevant applications, such as online advertisement and, more generally, recommendation systems. In many cases, however, these applications have a…

This work explores adaptive strategies for multi-armed bandits with causal structure, achieving optimal regret bounds.

Contextual bandits are online learners that, given an input, select an arm and receive a reward for that arm. They use the reward as a learning signal and aim to maximize the total reward over the inputs. Contextual bandits are commonly used to solve recommendation or ranking problems. This paper considers a learning s…

New attack manipulates UCB algorithm, new defense algorithm reduces pseudo-regret.

DOPL learns from preference feedback to solve RMAB problems.

We consider a setting where multiple players sequentially choose among a common set of actions (arms). Motivated by a cognitive radio networks application, we assume that players incur a loss upon colliding, and that communication between players is not possible. Existing approaches assume that the system is stationary…

New algorithm tackles non-stationary delayed feedback in recommender systems.

We consider a scenario where an agent has multiple available strategies to explore an unknown environment. For each new interaction with the environment, the agent must select which exploration strategy to use. We provide a new strategy-agnostic method that treat the situation as a Multi-Armed Bandits problem where the…

In machine learning, the notion of multi-armed bandits refers to a class of online learning problems, in which an agent is supposed to simultaneously explore and exploit a given set of choice alternatives in the course of a sequential decision process. In the standard setting, the agent learns from stochastic feedback …

Next generation networks are expected to be ultradense and aim to explore spectrum sharing paradigm that allows users to communicate in licensed, shared as well as unlicensed spectrum. Such ultra-dense networks will incur significant signaling load at base stations leading to a negative effect on spectrum and energy ef…

Autonomous systems can be used to search for sparse signals in a large space; e.g., aerial robots can be deployed to localize threats, detect gas leaks, or respond to distress calls. Intuitively, search algorithms may increase efficiency by collecting aggregate measurements summarizing large contiguous regions. However…

We consider a stochastic linear bandit problem with multiple users, where the relationship between users is captured by an underlying graph and user preferences are represented as smooth signals on the graph. We introduce a novel bandit algorithm where the smoothness prior is imposed via the random-walk graph Laplacian…

Enhances preference learning by incorporating response times into binary choices.

New algorithms optimize decision-making under uncertainty with graph information.

New algorithm optimizes long-term user satisfaction in recommendation systems.

The paper examines A/B tests in recommendation systems to detect biased algorithm comparisons due to shared data.

Paper proposes a risk-aware decision-making framework for real-world sequential decisions.

Multi-user multi-armed bandits have emerged as a good model for uncoordinated spectrum access problems. In this paper we consider the scenario where users cannot communicate with each other. In addition, the environment may appear differently to different users, ${i.e.}$, the mean rewards as observed by different users…

New algorithm optimizes for long-term user satisfaction in delayed reward settings.

Develops a flexible batched experimentation framework for limited adaptivity.

A learning algorithm optimizes beamforming for holographic transceivers in far-field communication.

Communication networks shared by many users are a widespread challenge nowadays. In this paper we address several aspects of this challenge simultaneously: learning unknown stochastic network characteristics, sharing resources with other users while keeping coordination overhead to a minimum. The proposed solution comb…

Improved RCPs for MABs using normalized weight functions.

New algorithms tackle RKHS bandits with reduced complexity and improved performance.

Unified formulation bridges adversarial and nonstationary bandits.

Paper tackles LDP bandits learning with improved results and sub-linear regret.

Paper solves stochastic contextual linear bandits using linear bandit algorithms.

Graph-Triggered Bandits unify rested and restless bandits with graph-defined arm interactions.

New definition resolves ambiguity in non-stationary bandit classification.

Unified approach for non-stationary and clustered bandits.

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