SCOBO: Sparsity-Aware Comparison Oracle Based Optimization

10/06/2020
by   HanQin Cai, et al.
6

We study derivative-free optimization for convex functions where we further assume that function evaluations are unavailable. Instead, one only has access to a comparison oracle, which, given two points x and y, and returns a single bit of information indicating which point has larger function value, f(x) or f(y), with some probability of being incorrect. This probability may be constant or it may depend on |f(x)-f(y)|. Previous algorithms for this problem have been hampered by a query complexity which is polynomially dependent on the problem dimension, d. We propose a novel algorithm that breaks this dependence: it has query complexity only logarithmically dependent on d if the function in addition has low dimensional structure that can be exploited. Numerical experiments on synthetic data and the MuJoCo dataset show that our algorithm outperforms state-of-the-art methods for comparison based optimization, and is even competitive with other derivative-free algorithms that require explicit function evaluations.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
04/08/2018

An Accelerated Directional Derivative Method for Smooth Stochastic Convex Optimization

We consider smooth stochastic convex optimization problems in the contex...
research
10/13/2020

High-Order Oracle Complexity of Smooth and Strongly Convex Optimization

In this note, we consider the complexity of optimizing a highly smooth (...
research
09/11/2012

Query Complexity of Derivative-Free Optimization

This paper provides lower bounds on the convergence rate of Derivative F...
research
10/26/2020

Query Complexity of k-NN based Mode Estimation

Motivated by the mode estimation problem of an unknown multivariate prob...
research
11/03/2020

Greedy k-Center from Noisy Distance Samples

We study a variant of the canonical k-center problem over a set of verti...
research
02/08/2023

Adaptive State-Dependent Diffusion for Derivative-Free Optimization

This paper develops and analyzes a stochastic derivative-free optimizati...
research
08/08/2017

Derivative-Based Optimization with a Non-Smooth Simulated Criterion

Indirect inference requires simulating realizations of endogenous variab...

Please sign up or login with your details

Forgot password? Click here to reset