LGQMMLJun 14, 2020

Autofocused oracles for model-based design

arXiv:2006.08052v288 citations
AI Analysis

This addresses a bottleneck in model-based design for applications like protein and materials engineering, offering a novel method to improve design outcomes.

The paper tackles the problem of data-driven design where regression models are used beyond their training regions, proposing autofocused oracles that retrain the model during the design process. It demonstrates empirical promise, though no concrete numbers are provided in the abstract.

Data-driven design is making headway into a number of application areas, including protein, small-molecule, and materials engineering. The design goal is to construct an object with desired properties, such as a protein that binds to a therapeutic target, or a superconducting material with a higher critical temperature than previously observed. To that end, costly experimental measurements are being replaced with calls to high-capacity regression models trained on labeled data, which can be leveraged in an in silico search for design candidates. However, the design goal necessitates moving into regions of the design space beyond where such models were trained. Therefore, one can ask: should the regression model be altered as the design algorithm explores the design space, in the absence of new data? Herein, we answer this question in the affirmative. In particular, we (i) formalize the data-driven design problem as a non-zero-sum game, (ii) develop a principled strategy for retraining the regression model as the design algorithm proceeds---what we refer to as autofocusing, and (iii) demonstrate the promise of autofocusing empirically.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes