A discrete version of CMA-ES

12/27/2018
by   Eric Benhamou, et al.
0

Modern machine learning uses more and more advanced optimization techniques to find optimal hyper parameters. Whenever the objective function is non-convex, non continuous and with potentially multiple local minima, standard gradient descent optimization methods fail. A last resource and very different method is to assume that the optimum(s), not necessarily unique, is/are distributed according to a distribution and iteratively to adapt the distribution according to tested points. These strategies originated in the early 1960s, named Evolution Strategy (ES) have culminated with the CMA-ES (Covariance Matrix Adaptation) ES. It relies on a multi variate normal distribution and is supposed to be state of the art for general optimization program. However, it is far from being optimal for discrete variables. In this paper, we extend the method to multivariate binomial correlated distributions. For such a distribution, we show that it shares similar features to the multi variate normal: independence and correlation is equivalent and correlation is efficiently modeled by interaction between different variables. We discuss this distribution in the framework of the exponential family. We prove that the model can estimate not only pairwise interactions among the two variables but also is capable of modeling higher order interactions. This allows creating a version of CMA ES that can accommodate efficiently discrete variables. We provide the corresponding algorithm and conclude.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
04/21/2014

A Computationally Efficient Limited Memory CMA-ES for Large Scale Optimization

We propose a computationally efficient limited memory Covariance Matrix ...
research
06/10/2014

Maximum Likelihood-based Online Adaptation of Hyper-parameters in CMA-ES

The Covariance Matrix Adaptation Evolution Strategy (CMA-ES) is widely a...
research
04/04/2016

The CMA Evolution Strategy: A Tutorial

This tutorial introduces the CMA Evolution Strategy (ES), where CMA stan...
research
03/21/2018

Hiding higher order cross-correlations of multivariate data using Archimedean copulas

In this paper we present the algorithm that changes the subset of margin...
research
02/16/2022

How to Fill the Optimum Set? Population Gradient Descent with Harmless Diversity

Although traditional optimization methods focus on finding a single opti...
research
05/07/2023

Inferring Local Structure from Pairwise Correlations

To construct models of large, multivariate complex systems, such as thos...

Please sign up or login with your details

Forgot password? Click here to reset