Continuum-Armed Bandits: A Function Space Perspective

10/15/2020
by   Shashank Singh, et al.
0

Continuum-armed bandits (a.k.a., black-box or 0^th-order optimization) involves optimizing an unknown objective function given an oracle that evaluates the function at a query point, with the goal of using as few query points as possible. In the most well-studied case, the objective function is assumed to be Lipschitz continuous and minimax rates of simple and cumulative regrets are known in both noiseless and noisy settings. This paper studies continuum-armed bandits under more general smoothness conditions, namely Besov smoothness conditions, on the objective function. In both noiseless and noisy conditions, we derive minimax rates under simple and cumulative regrets. Our results show that minimax rates over objective functions in a Besov space are identical to minimax rates over objective functions in the smallest Hölder space into which the Besov space embeds.

READ FULL TEXT
research
05/24/2019

Polynomial Cost of Adaptation for X -Armed Bandits

In the context of stochastic continuum-armed bandits, we present an algo...
research
01/02/2022

Thinking inside the box: A tutorial on grey-box Bayesian optimization

Bayesian optimization (BO) is a framework for global optimization of exp...
research
11/22/2022

Transfer Learning for Contextual Multi-armed Bandits

Motivated by a range of applications, we study in this paper the problem...
research
10/18/2017

Minimax Linear Estimation at a Boundary Point

This paper characterizes the minimax linear estimator of the value of an...
research
12/01/2018

Hierarchical Genetic Algorithms with evolving objective functions

We propose a framework of genetic algorithms which use multi-level hiera...
research
07/29/2023

Faster Stochastic Algorithms for Minimax Optimization under Polyak–Łojasiewicz Conditions

This paper considers stochastic first-order algorithms for minimax optim...
research
04/01/2016

COCO: The Bi-objective Black Box Optimization Benchmarking (bbob-biobj) Test Suite

The bbob-biobj test suite contains 55 bi-objective functions in continuo...

Please sign up or login with your details

Forgot password? Click here to reset