Non-stochastic Best Arm Identification and Hyperparameter Optimization

02/27/2015
by   Kevin Jamieson, et al.
0

Motivated by the task of hyperparameter optimization, we introduce the non-stochastic best-arm identification problem. Within the multi-armed bandit literature, the cumulative regret objective enjoys algorithms and analyses for both the non-stochastic and stochastic settings while to the best of our knowledge, the best-arm identification framework has only been considered in the stochastic setting. We introduce the non-stochastic setting under this framework, identify a known algorithm that is well-suited for this setting, and analyze its behavior. Next, by leveraging the iterative nature of standard machine learning algorithms, we cast hyperparameter optimization as an instance of non-stochastic best-arm identification, and empirically evaluate our proposed algorithm on this task. Our empirical results show that, by allocating more resources to promising hyperparameter settings, we typically achieve comparable test accuracies an order of magnitude faster than baseline methods.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
12/09/2020

Streaming Algorithms for Stochastic Multi-armed Bandits

We study the Stochastic Multi-armed Bandit problem under bounded arm-mem...
research
05/29/2017

Improving the Expected Improvement Algorithm

The expected improvement (EI) algorithm is a popular strategy for inform...
research
03/29/2018

Best arm identification in multi-armed bandits with delayed feedback

We propose a generalization of the best arm identification problem in st...
research
03/13/2023

Differential Good Arm Identification

This paper targets a variant of the stochastic multi-armed bandit proble...
research
03/14/2023

Best arm identification in rare events

We consider the best arm identification problem in the stochastic multi-...
research
08/12/2015

No Regret Bound for Extreme Bandits

Algorithms for hyperparameter optimization abound, all of which work wel...
research
09/16/2021

Policy Choice and Best Arm Identification: Comments on "Adaptive Treatment Assignment in Experiments for Policy Choice"

Adaptive experimental design for efficient decision-making is an importa...

Please sign up or login with your details

Forgot password? Click here to reset