[PDF] A Gang of Bandits | Semantic Scholar (2024)

This paper develops a collaborative contextual bandit algorithm, in which the adjacency graph among users is leveraged to share context and payoffs among neighboring users while online updating, and rigorously proves an improved upper regret bound.

This paper formalizes the networked bandit problem and proposes an algorithm that considers not only the selected arm, but also the relationships between arms, in that it decides an arm depending on integrated confidence sets constructed from historical data.

This paper explores the process of replicating the experiments and results from A Gang of Bandits in order to validate the paper and formalize the question about recommendation systems to be a multi-armed ban-dit problem.

This work proposes CLUB-HG, a novel algorithm that integrates a game-theoretic approach into clustering inference and discovers the underlying users’ clusters inContextual bandit algorithms.

This thesis goes beyond the well-studied multi-armed bandit model to consider structured bandit settings and their applications, and proposes a bootstrapping approach and establishes theoretical regret bounds for it.

The proposed ClexB policy for online RecSys explores knowledge transfer and further aids the inferences about user interests and estimates user clustering more accurately and with less uncertainty via explorable-clustering.

Two learning algorithms are presented, GABA-I and GABA-II, which exploit the network structure to bias towards functions of low Ψ values and highlight improvements of both algorithms over running independent standard MABs across users.

BARE is proposed, a bandit strategy for which a regret guarantee is proved that scales with the detectable dimension, a problem dependent quantity that is often much smaller than the number of nodes.

This paper seeks to theoretically understand the problem of minimizing regret in an N users heterogeneous stochastic linear bandits framework by studying the problem of minimizing regret in an N users heterogeneous stochastic linear bandits framework.

This work proposes an algorithm to divide the population of users into multiple clusters, and to customize the bandits to each cluster, and this clustering is dynamic, i.e., users can switch from one cluster to another, as their preferences change.

...

...

This work shows that the probability of playing a suboptimal arm at a peer in iteration t = Ω(log N) is proportional to 1/(Nt) where N denotes the number of peers participating in the network.

This work considers similarity information in the setting of contextual bandits, a natural extension of the basic MAB problem, and presents algorithms that are based on adaptive partitions, and take advantage of "benign" payoffs and context arrivals without sacrificing the worst-case performance.

This paper considers stochastic bandits with side observations, a model that accounts for both the exploration/exploitation dilemma and relationships between arms and provides efficient algorithms based on upper confidence bounds to leverage this additional information and derive new bounds improving on standard regret guarantees.

The investigations in this work reveal the significant gains that can be obtained even through static network-aware policies, and proposes a randomized policy that explores actions for each user at a rate that is a function of her network position.

A collaborative and adaptive distributed allocation rule DA is proposed and is shown to achieve the lower bound on the expected average regret for a connected inter-bandit communication network.

This work model personalized recommendation of news articles as a contextual bandit problem, a principled approach in which a learning algorithm sequentially selects articles to serve users based on contextual information about the users and articles, while simultaneously adapting its article-selection strategy based on user-click feedback to maximize total user clicks.

An O (√ Td ln (KT ln(T )/δ) ) regret bound is proved that holds with probability 1− δ for the simplest known upper confidence bound algorithm for this problem.

A simple modification of Auer's UCB algorithm achieves with high probability constant regret and improves the regret bound by a logarithmic factor, though experiments show a vast improvement.

A nearly complete characterization of the classical stochastic k-armed bandit problem in terms of both upper and lower bounds for the regret is given, and two variants of an algorithm based on the idea of “upper confidence bounds” are presented.

Practical algorithms with provable regret guarantees are developed, which depend on non-trivial graph-theoretic properties of the information feedback structure and partially-matching lower bounds are provided.

...

...