Parallel Distributed Block Coordinate Descent Methods based on Pairwise Comparison Oracle

TL;DR

This paper introduces a parallel block coordinate descent algorithm that optimizes functions using only pairwise comparisons, eliminating the need for gradient or function value computations, and demonstrates its efficiency and convergence properties.

Contribution

The paper proposes a novel pairwise comparison-based block coordinate descent method that is parallelizable and does not require gradient or function evaluations.

Findings

Efficiently finds the optimal solution compared to existing pairwise comparison methods.

Provides an upper bound on the convergence rate.

Algorithm is suitable for parallel implementation.

Abstract

This paper provides a block coordinate descent algorithm to solve unconstrained optimization problems. In our algorithm, computation of function values or gradients is not required. Instead, pairwise comparison of function values is used. Our algorithm consists of two steps; one is the direction estimate step and the other is the search step. Both steps require only pairwise comparison of function values, which tells us only the order of function values over two points. In the direction estimate step, a Newton type search direction is estimated. A computation method like block coordinate descent methods is used with the pairwise comparison. In the search step, a numerical solution is updated along the estimated direction. The computation in the direction estimate step can be easily parallelized, and thus, the algorithm works efficiently to find the minimizer of the objective function. Also, we show an upper bound of the convergence rate. In numerical experiments, we show that our method efficiently finds the optimal solution compared to some existing methods based on the pairwise comparison.