# Adaptive Divergence for Rapid Adversarial Optimization

arXiv: https://arxiv.org/abs/1912.00520 · HTML: https://mlsanity.com/paper/1912.00520/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 Dec 2019.

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

- [Meta-learning accelerates detector design optimization](https://mlsanity.com/paper/2609.35827/) (2026)

## Abstract (arXiv)

Adversarial Optimization (AO) provides a reliable, practical way to match two implicitly defined distributions, one of which is usually represented by a sample of real data, and the other is defined by a generator. Typically, AO involves training of a high-capacity model on each step of the optimization. In this work, we consider computationally heavy generators, for which training of high-capacity models is associated with substantial computational costs. To address this problem, we introduce a novel family of divergences, which varies the capacity of the underlying model, and allows for a significant acceleration with respect to the number of samples drawn from the generator. We demonstrate the performance of the proposed divergences on several tasks, including tuning parameters of a physics simulator, namely, Pythia event generator.