PROTES: Probabilistic Optimization with Tensor Sampling

Anastasia Batsheva, A. Chertkov, G. Ryzhakov, I. Oseledets
1/1/2023

No official code found. Best implementation: AndreiChertkov/teneva (69 stars, MIT, last commit 2025-11-20). 1 more below.

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 $2^{100}$. In numerical experiments, both on analytic model functions and on complex problems, PROTES outperforms existing popular discrete optimization methods (Particle Swarm Optimization, Covariance Matrix Adaptation, Differential Evolution, and others).

View on arXivView PDF

Code Implementations(2)

AndreiChertkov/tenevaCommunity100%
MIT

A framework based on the tensor train decomposition for working with multivariate functions and multidimensional arrays

691PythonNov 25, 202011 months agoMIT
approximation-algorithmslow-rank-approximationsurrogate-modellingsurrogate-modelstensor-decomposition+3 more
anabatsh/PROTESCommunity100%

Gradient-free optimization method for the multidimensional arrays and discretized multivariate functions based on the tensor train (TT) format.

415PythonFeb 9, 20231 years ago
discrete-optimizationgradient-free-optimizationmultidimensional-arraysoptimizationtensor-decomposition+1 more

Similar Papers

Polynomial-Model-Based Optimization for Blackbox Objectives

84% match2023

Investigating Bayesian optimization for expensive-to-evaluate black box functions: Application in fluid dynamics

83% match2022

Posterior Inference with Diffusion Models for High-dimensional Black-box Optimization

81% match1 repo152025

Evolution Strategies as a Scalable Alternative to Reinforcement Learning

81% match1 repo1.6k2017

Bayesian Optimization with High-Dimensional Outputs

80% match1 repo162021

BILBO: BILevel Bayesian Optimization

80% match1 repo72025

Cite this paper

@article{batsheva2023protes,
  title  = {PROTES: Probabilistic Optimization with Tensor Sampling},
  author = {Anastasia Batsheva and A. Chertkov and G. Ryzhakov and I. Oseledets},
  year   = {2023},
  eprint = {2301.12162},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/pdf/2301.12162},
  journal = {NEURIPS 2023 2023}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2301.12162.svg)](https://codeofpaper.com/paper/2301.12162)

Discussion