# Sequential stochastic blackbox optimization with zeroth-order gradient estimators

arXiv: https://arxiv.org/abs/2305.19450 · HTML: https://mlsanity.com/paper/2305.19450/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 30 May 2023.

## Built on by (most cited first, 1 of 1)

- [Global Optimisation of Black-Box Functions with Generative Models in the Wasserstein Space](https://mlsanity.com/paper/2407.11917/) (2024)

## Abstract (arXiv)

This work considers stochastic optimization problems in which the objective function values can only be computed by a blackbox corrupted by some random noise following an unknown distribution. The proposed method is based on sequential stochastic optimization (SSO): the original problem is decomposed into a sequence of subproblems. Each of these subproblems is solved using a zeroth order version of a sign stochastic gradient descent with momentum algorithm (ZO-Signum) and with an increasingly fine precision. This decomposition allows a good exploration of the space while maintaining the efficiency of the algorithm once it gets close to the solution. Under Lipschitz continuity assumption on the blackbox, a convergence rate in expectation is derived for the ZO-signum algorithm. Moreover, if the blackbox is smooth and convex or locally convex around its minima, a convergence rate to an ε-optimal point of the problem may be obtained for the SSO algorithm. Numerical experiments are conducted to compare the SSO algorithm with other state-of-the-art algorithms and to demonstrate its competitiveness.