On Universally Optimal Algorithms for A/B Testing

Sequential design of experiments

Chernoff, H · 1959

Earlier work this paper cites.

Asymptotically efficient adaptive allocation rules

Lai, T. L. and Robbins, H · 1985

Earlier work this paper cites.

A large deviations perspective on ordinal optimization

Glynn, P. and Juneja, S · 2004

Earlier work this paper cites.

Action elimination and stopping conditions for the multi-armed bandit and reinforcement learning problems

Even-Dar, E., Mannor, S., Mansour, Y., and Mahadevan, S · 2006

Earlier work this paper cites.

Best arm identification in multi-armed bandits

Audibert, J.-Y., Bubeck, S., and Munos, R · 2010

Earlier work this paper cites.

Pure exploration in finitely-armed and continuous-armed bandits

Bubeck, S., Munos, R., and Stoltz, G · 2011

Earlier work this paper cites.

Best arm identification: A unified approach to fixed budget and fixed confidence

Gabillon, V., Ghavamzadeh, M., and Lazaric, A · 2012

Earlier work this paper cites.

Kullback–leibler upper confidence bounds for optimal sequential allocation

Cappé, O., Garivier, A., Maillard, O.-A., Munos, R., Stoltz, G., et al · 2013

Cited alongside, same era.

Almost optimal exploration in multi-armed bandits

Karnin, Z., Koren, T., and Somekh, O · 2013

Cited alongside, same era.

Unimodal bandits: Regret lower bounds and optimal algorithms

Combes, R. and Proutiere, A · 2014

Cited alongside, same era.

On the complexity of A/B testing

Kaufmann, E., Cappé, O., and Garivier, A · 2014

Cited alongside, same era.

Tight (lower) bounds for the fixed budget best arm identification bandit problem

Carpentier, A. and Locatelli, A · 2016

Cited alongside, same era.

Optimal best arm identification with fixed confidence

Garivier, A. and Kaufmann, E · 2016

Cited alongside, same era.

Explore first, exploit next: The true shape of regret in bandit problems

Garivier, A., Ménard, P., and Stoltz, G · 2019

Later among the works it cites.

Simple bayesian algorithms for best-arm identification

Russo, D · 2020

Later among the works it cites.

Policy choice and best arm identification: Asymptotic analysis of exploration sampling

Original

Ariu, K., Kato, M., Komiyama, J., McAlinn, K., and Qin, C · 2021

Later among the works it cites.

Minimax optimal algorithms for fixed-budget best arm identification

Komiyama, J., Tsuchiya, T., and Honda, J · 2022

Later among the works it cites.

Open problem: Optimal best arm identification with fixed-budget

Qin, C · 2022

Later among the works it cites.

On the existence of a complexity in fixed budget bandit identification