GPdoemd: a Python package for design of experiments for model discrimination
This work addresses the challenge of model discrimination for researchers in fields like systems biology or engineering who need to identify accurate models from multiple hypotheses with limited data, representing an incremental improvement through novel method integration.
The paper tackles the problem of discriminating between rival mathematical models when experimental data is insufficient, by proposing a new design criterion using Jensen-Rényi divergence and developing a method that replaces black-box models with Gaussian process surrogates to handle model uncertainty. Results demonstrate that these contributions perform well on both classical and new test instances.
Model discrimination identifies a mathematical model that usefully explains and predicts a given system's behaviour. Researchers will often have several models, i.e. hypotheses, about an underlying system mechanism, but insufficient experimental data to discriminate between the models, i.e. discard inaccurate models. Given rival mathematical models and an initial experimental data set, optimal design of experiments suggests maximally informative experimental observations that maximise a design criterion weighted by prediction uncertainty. The model uncertainty requires gradients, which may not be readily available for black-box models. This paper (i) proposes a new design criterion using the Jensen-Rényi divergence, and (ii) develops a novel method replacing black-box models with Gaussian process surrogates. Using the surrogates, we marginalise out the model parameters with approximate inference. Results show these contributions working well for both classical and new test instances. We also (iii) introduce and discuss GPdoemd, the open-source implementation of the Gaussian process surrogate method.