PROTES: Probabilistic Optimization with Tensor Sampling

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).

PDF NeurIPS OpenReview Semantic Scholar

Cite

Text

Batsheva et al. "PROTES: Probabilistic Optimization with Tensor Sampling." Neural Information Processing Systems, 2023.

Markdown

[Batsheva et al. "PROTES: Probabilistic Optimization with Tensor Sampling." Neural Information Processing Systems, 2023.](https://mlanthology.org/neurips/2023/batsheva2023neurips-protes/)

BibTeX

@inproceedings{batsheva2023neurips-protes,
  title     = {{PROTES: Probabilistic Optimization with Tensor Sampling}},
  author    = {Batsheva, Anastasiia and Chertkov, Andrei and Ryzhakov, Gleb and Oseledets, Ivan},
  booktitle = {Neural Information Processing Systems},
  year      = {2023},
  url       = {https://mlanthology.org/neurips/2023/batsheva2023neurips-protes/}
}