Boltzmann Tuning of Generative Models

by   Victor Berger, et al.

The paper focuses on the a posteriori tuning of a generative model in order to favor the generation of good instances in the sense of some external differentiable criterion. The proposed approach, called Boltzmann Tuning of Generative Models (BTGM), applies to a wide range of applications. It covers conditional generative modelling as a particular case, and offers an affordable alternative to rejection sampling. The contribution of the paper is twofold. Firstly, the objective is formalized and tackled as a well-posed optimization problem; a practical methodology is proposed to choose among the candidate criteria representing the same goal, the one best suited to efficiently learn a tuned generative model. Secondly, the merits of the approach are demonstrated on a real-world application, in the context of robust design for energy policies, showing the ability of BTGM to sample the extreme regions of the considered criteria.



There are no comments yet.


page 24

page 25

page 28


Conditional Sampling from Invertible Generative Models with Applications to Inverse Problems

We consider uncertainty aware compressive sensing when the prior distrib...

Tractable loss function and color image generation of multinary restricted Boltzmann machine

The restricted Boltzmann machine (RBM) is a representative generative mo...

Composable Generative Models

Generative modeling has recently seen many exciting developments with th...

Regularising Inverse Problems with Generative Machine Learning Models

Deep neural network approaches to inverse imaging problems have produced...

A note on the evaluation of generative models

Probabilistic generative models can be used for compression, denoising, ...

Random-walk Based Generative Model for Classifying Document Networks

Document networks are found in various collections of real-world data, s...

Deep Ptych: Subsampled Fourier Ptychography using Generative Priors

This paper proposes a novel framework to regularize the highly ill-posed...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.