Variational Search Distributions

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Steinberg, Daniel M., Oliveira, Rafael, Ong, Cheng Soon, Bonilla, Edwin V.
Format:	Preprint
Published:	2024
Subjects:	Machine Learning G.3; G.2.1; I.2.6
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

_version_	1866909915733295104
author	Steinberg, Daniel M. Oliveira, Rafael Ong, Cheng Soon Bonilla, Edwin V.
author_facet	Steinberg, Daniel M. Oliveira, Rafael Ong, Cheng Soon Bonilla, Edwin V.
contents	We develop VSD, a method for conditioning a generative model of discrete, combinatorial designs on a rare desired class by efficiently evaluating a black-box (e.g. experiment, simulation) in a batch sequential manner. We call this task active generation; we formalize active generation's requirements and desiderata, and formulate a solution via variational inference. VSD uses off-the-shelf gradient based optimization routines, can learn powerful generative models for desirable designs, and can take advantage of scalable predictive models. We derive asymptotic convergence rates for learning the true conditional generative distribution of designs with certain configurations of our method. After illustrating the generative model on images, we empirically demonstrate that VSD can outperform existing baseline methods on a set of real sequence-design problems in various protein and DNA/RNA engineering tasks.
format	Preprint
id	arxiv_https___arxiv_org_abs_2409_06142
institution	arXiv
publishDate	2024
record_format	arxiv
spellingShingle	Variational Search Distributions Steinberg, Daniel M. Oliveira, Rafael Ong, Cheng Soon Bonilla, Edwin V. Machine Learning G.3; G.2.1; I.2.6 We develop VSD, a method for conditioning a generative model of discrete, combinatorial designs on a rare desired class by efficiently evaluating a black-box (e.g. experiment, simulation) in a batch sequential manner. We call this task active generation; we formalize active generation's requirements and desiderata, and formulate a solution via variational inference. VSD uses off-the-shelf gradient based optimization routines, can learn powerful generative models for desirable designs, and can take advantage of scalable predictive models. We derive asymptotic convergence rates for learning the true conditional generative distribution of designs with certain configurations of our method. After illustrating the generative model on images, we empirically demonstrate that VSD can outperform existing baseline methods on a set of real sequence-design problems in various protein and DNA/RNA engineering tasks.
title	Variational Search Distributions
topic	Machine Learning G.3; G.2.1; I.2.6
url	https://arxiv.org/abs/2409.06142