Adaptive Divergence for Rapid Adversarial Optimization

12/01/2019
by   Maxim Borisyak, et al.
0

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.

READ FULL TEXT

page 1

page 12

research
03/09/2021

BROOD: Bilevel and Robust Optimization and Outlier Detection for Efficient Tuning of High-Energy Physics Event Generators

The parameters in Monte Carlo (MC) event generators are tuned on experim...
research
02/28/2023

Towards Addressing GAN Training Instabilities: Dual-objective GANs with Tunable Parameters

In an effort to address the training instabilities of GANs, we introduce...
research
01/16/2019

Class-Balanced Loss Based on Effective Number of Samples

With the rapid increase of large-scale, real-world datasets, it becomes ...
research
09/21/2010

A family of statistical symmetric divergences based on Jensen's inequality

We introduce a novel parametric family of symmetric information-theoreti...
research
09/18/2023

Dual Student Networks for Data-Free Model Stealing

Existing data-free model stealing methods use a generator to produce sam...
research
05/27/2023

Learning Capacity: A Measure of the Effective Dimensionality of a Model

We exploit a formal correspondence between thermodynamics and inference,...
research
09/17/2020

Integration of AI and mechanistic modeling in generative adversarial networks for stochastic inverse problems

The problem of finding distributions of input parameters for determinist...

Please sign up or login with your details

Forgot password? Click here to reset