Dueling Convex Optimization with General Preferences
Abstract
We address the problem of \emph{convex optimization with dueling feedback}, where the goal is to minimize a convex function given a weaker form of \emph{dueling} feedback. Each query consists of two points and the dueling feedback returns a (noisy) single-bit binary comparison of the function values of the two queried points. The translation of the function values to the single comparison bit is through a \emph{transfer function}. This problem has been addressed previously for some restricted classes of transfer functions, but here we consider a very general transfer function class which includes all functions that can be approximated by a finite polynomial with a minimal degree . Our main contribution is an efficient algorithm with convergence rate of for a smooth convex objective function, and an optimal rate of when the objective is smooth and strongly convex.
Cite
@article{arxiv.2210.02562,
title = {Dueling Convex Optimization with General Preferences},
author = {Aadirupa Saha and Tomer Koren and Yishay Mansour},
journal= {arXiv preprint arXiv:2210.02562},
year = {2022}
}