Design by adaptive sampling

TL;DR

This paper introduces an adaptive sampling framework combining generative models with predictive oracles to optimize input design for various properties, outperforming existing methods especially in deterministic settings.

Contribution

The paper proposes a novel probabilistic modeling and adaptive sampling approach for input design that effectively handles stochastic oracles and outperforms prior techniques.

Findings

Outperforms recent methods in deterministic oracle maximization

Can handle more general input design problems

Effective in optimizing properties across diverse applications

Abstract

We present a probabilistic modeling framework and adaptive sampling algorithm wherein unsupervised generative models are combined with black box predictive models to tackle the problem of input design. In input design, one is given one or more stochastic "oracle" predictive functions, each of which maps from the input design space (e.g. DNA sequences or images) to a distribution over a property of interest (e.g. protein fluorescence or image content). Given such stochastic oracles, the problem is to find an input that is expected to maximize one or more properties, or to achieve a specified value of one or more properties, or any combination thereof. We demonstrate experimentally that our approach substantially outperforms other recently presented methods for tackling a specific version of this problem, namely, maximization when the oracle is assumed to be deterministic and unbiased. We also demonstrate that our method can tackle more general versions of the problem.