A Minimalist Bayesian Framework for Stochastic Optimization

Kaizheng Wang

Abstract

The Bayesian paradigm offers principled tools for sequential decision-making under uncertainty, but its reliance on a probabilistic model for all parameters can hinder the incorporation of complex structural constraints. We introduce a minimalist Bayesian framework that places a prior only on the component of interest, such as the location of the optimum. Nuisance parameters are eliminated via profile likelihood, which naturally handles constraints. As a direct instantiation, we develop a MINimalist Thompson Sampling (MINTS) algorithm. Our framework accommodates structured problems, including continuum-armed Lipschitz bandits and dynamic pricing. It also provides a probabilistic lens on classical convex optimization algorithms such as the center of gravity and ellipsoid methods. We further analyze MINTS for multi-armed bandits and establish near-optimal regret guarantees.
BibTeX
@misc{wang2025minimalist,
  author = {Kaizheng Wang},
  title = {{A Minimalist Bayesian Framework for Stochastic Optimization}},
  year = {2025},
  eprint = {2509.07030},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2509.07030},
}

Loading related content...

Figure