PROTES: Probabilistic Optimization with Tensor Sampling
Anastasia Batsheva, Andrei Chertkov, Gleb Ryzhakov, Ivan Oseledets
Abstract
We developed a new method PROTES for black-box optimization, which is based on the probabilistic sampling from a probability density function given in the low-parametric tensor train format. We tested it on complex multidimensional arrays and discretized multivariable functions taken, among others, from real-world applications, including unconstrained binary optimization and optimal control problems, for which the possible number of elements is up to $2^{1000}$. In numerical experiments, both on analytic model functions and on complex problems, PROTES outperforms popular discrete optimization methods (Particle Swarm Optimization, Covariance Matrix Adaptation, Differential Evolution, and others).
BibTeX
@inproceedings{
batsheva2023protes,
title={{PROTES}: Probabilistic Optimization with Tensor Sampling},
author={Anastasia Batsheva and Andrei Chertkov and Gleb Ryzhakov and Ivan Oseledets},
booktitle={Thirty-seventh Conference on Neural Information Processing Systems},
year={2023},
url={https://openreview.net/forum?id=R9R7YDOar1}
}