Procrastinated Tree Search: Black-box Optimization with Delayed, Noisy, and Multi-fidelity Feedback - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2022

Procrastinated Tree Search: Black-box Optimization with Delayed, Noisy, and Multi-fidelity Feedback

Debabrota Basu

Abstract

In black-box optimization problems, we aim to maximize an unknown objective function, where the function is only accessible through feedbacks of an evaluation or simulation oracle. In real-life, the feedbacks of such oracles are often noisy and available after some unknown delay that may depend on the computation time of the oracle. Additionally, if the exact evaluations are expensive but coarse approximations are available at a lower cost, the feedbacks can have multi-fidelity. In order to address this problem, we propose a generic extension of hierarchical optimistic tree search (HOO), called ProCrastinated Tree Search (PCTS), that flexibly accommodates a delay and noise-tolerant bandit algorithm. We provide a generic proof technique to quantify regret of PCTS under delayed, noisy, and multi-fidelity feedbacks. Specifically, we derive regret bounds of PCTS enabled with delayed-UCB1 (DUCB1) and delayed-UCB-V (DUCBV) algorithms. Given a horizon T, PCTS retains the regret bound of non-delayed HOO for expected delay of O (log T), and worsens by T^((1-α)/(d+ 2)) for expected delays of O (T^(1-α)) for α∈(0, 1]. We experimentally validate on multiple synthetic functions and hyperparameter tuning problems that PCTS outperforms the state-of-the-art black-box optimization methods for feedbacks with different noise levels, delays, and fidelity.
Fichier principal
Vignette du fichier
2110.07232v2 (1).pdf (2.21 Mo) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-03445909 , version 1 (06-09-2022)

Licence

Attribution - NonCommercial

Identifiers

Cite

Junxiong Wang, Debabrota Basu, Immanuel Trummer. Procrastinated Tree Search: Black-box Optimization with Delayed, Noisy, and Multi-fidelity Feedback. AAAI Conference on Artificial Intelligence, Feb 2022, Virtual, United States. pp.10381-10390. ⟨hal-03445909⟩
45 View
34 Download

Altmetric

Share

Gmail Facebook X LinkedIn More