20
2

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 pp. Our main contribution is an efficient algorithm with convergence rate of O~(ϵ4p)\smash{\widetilde O}(\epsilon^{-4p}) for a smooth convex objective function, and an optimal rate of O~(ϵ2p)\smash{\widetilde O}(\epsilon^{-2p}) when the objective is smooth and strongly convex.

View on arXiv
Comments on this paper