Publication

Overlapping Multi-Bandit Best Arm Identification

Volkan Cevher, Jonathan Mark Scarlett, Ilija Bogunovic
2019
Conference Papers

Abstract

In the multi-armed bandit literature, the multi-bandit best-arm identification problem consists of determining each best arm in a number of disjoint groups of arms, with as few total arm pulls as possible. In this paper, we introduce a variant of the multi-bandit problem with overlapping groups, and present two algorithms for this problem based on successive elimination and lower/upper confidence bounds (LUCB). We bound the number of total arm pulls required for high-probability best-arm identification in every group, and we complement these bounds with a near-matching algorithm-independent lower bound. In addition, we show that a specific choice of the groups recovers the top-k ranking problem.

Official source

https://infoscience.epfl.ch/entities/publication/f2a61d62-333d-4da1-bd62-e3724a12a0cf

About this result

This page is automatically generated and may contain information that is not correct, complete, up-to-date, or relevant to your search query. The same applies to every other page on this website. Please make sure to verify the information with EPFL's official sources.

Volkan Cevher, Jonathan Mark Scarlett, Ilija Bogunovic
2019
Conference Papers

Abstract

Official source

https://infoscience.epfl.ch/entities/publication/f2a61d62-333d-4da1-bd62-e3724a12a0cf

About this result

Related concepts (14)

Symmetric group

In abstract algebra, the symmetric group defined over any set is the group whose elements are all the bijections from the set to itself, and whose group operation is the composition of functions. In particular, the finite symmetric group defined over a finite set of symbols consists of the permutations that can be performed on the symbols. Since there are ( factorial) such permutation operations, the order (number of elements) of the symmetric group is .

Problem solving

Problem solving is the process of achieving a goal by overcoming obstacles, a frequent part of most activities. Problems in need of solutions range from simple personal tasks (e.g. how to turn on an appliance) to complex issues in business and technical fields. The former is an example of simple problem solving (SPS) addressing one issue, whereas the latter is complex problem solving (CPS) with multiple interrelated obstacles.

Lagrange's theorem (group theory)

In the mathematical field of group theory, Lagrange's theorem is a theorem that states that for any finite group G, the order (number of elements) of every subgroup of G divides the order of G. The theorem is named after Joseph-Louis Lagrange. The following variant states that for a subgroup of a finite group , not only is an integer, but its value is the index , defined as the number of left cosets of in . Lagrange's theorem This variant holds even if is infinite, provided that , , and are interpreted as cardinal numbers.

Related publications (25)

The Two Times Problem: Where Is the Problem?

Michael Herzog

Gruber et al. (2022) offered a framework how to explain "Physical time within human time", solving the 'two times problem: Here, I am asking whether such a problem exists at all. To question the question, I will appeal to neurobiological, evolutionary, and ...

Brill2024

Hands-on tasks make learning visible: a learning analytics lens on the development of mechanistic problem-solving expertise in makerspaces

Bertrand Roland Schneider, Richard Lee Davis

This study investigated the impact of participating in a year-long digital-fabrication course on high-school seniors' problem-solving skills, with a focus on problems involving mechanistic systems. The research questions centered on whether working in a ma ...

Springer2023

Approximation Algorithms for Allocation and Network Design

Etienne Michel François Bamas

In this thesis, we give new approximation algorithms for some NP-hard problems arising in resource allocation and network design. As a resource allocation problem, we study the Santa Claus problem (also known as the MaxMin Fair Allocation problem) in which ...

EPFL2023