# Gaussian Process Bandit Optimization of the Thermodynamic Variational Objective

arXiv: https://arxiv.org/abs/2010.15750 · HTML: https://mlsanity.com/paper/2010.15750/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 29 Oct 2020.

## Built on by (most cited first, 3 of 3)

- [Bayesian Generational Population-Based Training](https://mlsanity.com/paper/2207.09405/) (2022)
- [Distributionally Robust Bayesian Optimization with varphi-divergences](https://mlsanity.com/paper/2203.02128/) (2022)
- [Multi-armed bandits for resource efficient, online optimization of language model pre-training: the use case of dynamic masking](https://mlsanity.com/paper/2203.13151/) (2022)

## Abstract (arXiv)

Achieving the full promise of the Thermodynamic Variational Objective (TVO), a recently proposed variational lower bound on the log evidence involving a one-dimensional Riemann integral approximation, requires choosing a "schedule" of sorted discretization points. This paper introduces a bespoke Gaussian process bandit optimization method for automatically choosing these points. Our approach not only automates their one-time selection, but also dynamically adapts their positions over the course of optimization, leading to improved model learning and inference. We provide theoretical guarantees that our bandit optimization converges to the regret-minimizing choice of integration points. Empirical validation of our algorithm is provided in terms of improved learning and inference in Variational Autoencoders and Sigmoid Belief Networks.