Journal article · 2026 · Open access

VBO-MI: A Differentiable Black-Box Optimization Framework via Variational Mutual Information Estimation

Farhad Mirkarimi

Transactions on machine learning research · Published 17 October 2026 · DOI 10.48550/arxiv.2610.24491

Open full textView at the publisherCite this paper

In brief

“VBO-MI: A Differentiable Black-Box Optimization Framework via Variational Mutual Information Estimation” is a 2026 journal article by Farhad Mirkarimi, published in Transactions on machine learning research. OpenAlex counts 2 citations as of 19 November 2026, which puts it in the top 6% of works published in 2026 by citations. It is open access under a CC BY licence: the full text is free to read at Transactions on machine learning research.

Citations
2
Most cited in
2026 (2)
Field-weighted impact
4.82
References
33
Authors
1

Abstract

Many real-world tasks require optimizing expensive black-box functions accessible only through noisy evaluations, a setting commonly addressed with Bayesian optimization. While Gaussian processes(GPs) and Bayesian neural networks have driven significant progress, GP-based methods scale cubically with observations, and BNN-based approaches remain burdened by expensive posterior sampling such as Hamiltonian Monte Carlo, and inner-loop acquisition optimization in high-dimensional setting. In this work, we propose VBO-MI, a fully gradient-based BO framework that requires no assumptions on a Gaussian prior or a variational posterior family over $f$. While our framework uses gradient-based updates to train the internal action and information-estimation networks, it treats the objective function $f$ as a strict black box, requiring only zeroth-order evaluations. To enable end-to-end gradient flow, we employ an actor-critic architecture consisting of an action-net to navigate the input space and a variational critic to estimate a surrogate information signal for exploration. Additionally, we design a lightweight surrogate that approximates the objective from observed data using a replay buffer, which reduces the total required real function queries to one batch per iteration. We provide theoretical analysis for our framework, establishing convergence of its training objective and surrogate estimator, and showing, that near-optimal solutions exist. We evaluate our method on a diverse suite of benchmarks, including high-dimensional synthetic function and complex real-world tasks such as Rover Trajectory planning optimization, the Lunar Lander, and Pest Control problems. Our experiments demonstrate that VBO-MI provides the same or superior optimization performance over the various baselines.

Cite this paper

Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.

APA 7

Mirkarimi, F. (2026). VBO-MI: A Differentiable Black-Box Optimization Framework via Variational Mutual Information Estimation. Transactions on machine learning research. https://doi.org/10.48550/arxiv.2610.24491

MLA 9

Mirkarimi, Farhad. “VBO-MI: A Differentiable Black-Box Optimization Framework via Variational Mutual Information Estimation.” Transactions on machine learning research, 2026. https://doi.org/10.48550/arxiv.2610.24491.

Chicago

Mirkarimi, Farhad. 2026. “VBO-MI: A Differentiable Black-Box Optimization Framework via Variational Mutual Information Estimation.” Transactions on machine learning research. https://doi.org/10.48550/arxiv.2610.24491.

Harvard

Mirkarimi, F. (2026) ‘VBO-MI: A Differentiable Black-Box Optimization Framework via Variational Mutual Information Estimation’, Transactions on machine learning research. doi:10.48550/arxiv.2610.24491.

IEEE

F. Mirkarimi, “VBO-MI: A Differentiable Black-Box Optimization Framework via Variational Mutual Information Estimation,” Transactions on machine learning research, 2026, doi: 10.48550/arxiv.2610.24491.

BibTeX

@article{mirkarimi2026differentiable,
  title     = {{VBO-MI: A Differentiable Black-Box Optimization Framework via Variational Mutual Information Estimation}},
  author    = {Mirkarimi, Farhad},
  journal   = {Transactions on machine learning research},
  year      = {2026},
  doi       = {10.48550/arxiv.2610.24491},
  url       = {https://doi.org/10.48550/arxiv.2610.24491}
}

Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)

Topic and keywords

Social Sciences › Decision Sciences › Management Science and Operations Research › Advanced Bandit Algorithms Research

  • black-box optimization
  • actor-critic architecture
  • derivative-free optimization
  • surrogate models
  • replay buffer
  • exploration
  • high-dimensional optimization
  • lunar lander

Work with this paper

Most-cited papers in Decision Sciences

All highly cited Decision Sciences papers

Questions about this paper

How do I cite this paper in APA style?

Mirkarimi, F. (2026). VBO-MI: A Differentiable Black-Box Optimization Framework via Variational Mutual Information Estimation. Transactions on machine learning research. https://doi.org/10.48550/arxiv.2610.24491

How many times has this paper been cited?

2 times, according to OpenAlex on 19 November 2026. Google Scholar and Scopus count different sets of sources, so their numbers differ.

Is this paper free to read?

Yes. It is open access at Transactions on machine learning research: sign in and open the full text from this page.

Who wrote this paper?

Farhad Mirkarimi.

What is the DOI of this paper?

10.48550/arxiv.2610.24491, permanently at https://doi.org/10.48550/arxiv.2610.24491. Sign in and open it from this page.

Bibliographic data from OpenAlex (CC0), last checked 19 November 2026. ResearchGuru does not host this paper; once you are signed in, the links open it at the publisher or the repository that does.