Deep Adaptive Model-Based Design of Experiments

TL;DR

This paper introduces a deep learning approach for real-time, adaptive experimental design in nonlinear dynamical systems, reducing computational costs and enabling practical applications.

Contribution

It combines neural network policies with differentiable models, extending contrastive training for nuisance parameters, and demonstrates effectiveness on diverse dynamical systems.

Findings

Effective real-time experimental design across multiple systems

Reduced computational cost compared to traditional methods

Successful deployment on real-time systems

Abstract

Model-based design of experiments (MBDOE) is essential for efficient parameter estimation in nonlinear dynamical systems. However, conventional adaptive MBDOE requires costly posterior inference and design optimization between each experimental step, precluding real-time applications. We address this by combining Deep Adaptive Design (DAD), which amortizes sequential design into a neural network policy trained offline, with differentiable mechanistic models. For dynamical systems with known governing equations but uncertain parameters, we extend sequential contrastive training objectives to handle nuisance parameters and propose a transformer-based policy architecture that respects the temporal structure of dynamical systems. We demonstrate the approach on four systems of increasing complexity: a fed-batch bioreactor with Monod kinetics, a Haldane bioreactor with uncertain substrate inhibition, a two-compartment pharmacokinetic model with nuisance clearance parameters, and a DC motor for real-time deployment.