Learning the distribution with largest mean: two bandit frameworks
By Emilie Kaufmann, Aurélien Garivier. 2017
21 citations recorded by the source corpus.
Over the past few years, the multi-armed bandit model has become increasingly popular in the machine learning community, partly because of applications including online content optimization. This paper reviews two different sequential learning tasks that have been considered in the bandit literature ; they can be formulated as (sequentially) learning which distribution has the highest mean among a set of distributions, with some constraints on the learning process. For both of them (regret minimization and best arm identification) we present recent, asymptotically optimal algorithms. We compare the behaviors of the sampling rule of each algorithm as well as the complexity terms associated to each problem.
Subfields: Artificial Intelligence, Management Science and Operations Research
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Tong Yu
- Hong Zhu
- Emilie Kaufmann
- Gaurav Menghani
- Daniel Russo
- Tor Lattimore
- Aurélien Garivier
- Csaba Szepesvari
In Management Science and Operations Research
- Andrée Delahaye-Duriez
- Clémence Réda
- Tong Yu
- Hong Zhu
- Emilie Kaufmann
- Daniel Russo
- Tor Lattimore
- Aurélien Garivier
Citations in the corpus
- Hyper-Parameter Optimization: A Review of Algorithms and Applications (2020, background): “Bandit processes are a special type of Markov Decision Process with several possible choices (Kaufmann and Garivier, 2017), and they have a long history of stochastic setting.”
- Machine learning applications in drug development (2019, background): “See the following referenced paper [36] for a comparison between bandit problems.”