Guiding the Sequential Experiments in Autonomous Experimentation Platforms through EI-based Bayesian Optimization and Bayesian Model Averaging
This work addresses the challenge of efficient material design for manufacturing by improving prediction accuracy, though it is incremental as it builds on existing BO methods by incorporating model uncertainty.
The paper tackles the problem of guiding sequential experiments in autonomous experimentation platforms by comparing a traditional Bayesian Optimization (BO) approach with an Expected Improvement (EI) acquisition function to a Bayesian Model Averaging (BMA) method that accounts for model uncertainty, finding that BMA reduces prediction error, as evidenced by lower RMSE on a real-life steel fatigue dataset.
Autonomous Experimentation Platforms (AEPs) are advanced manufacturing platforms that, under intelligent control, can sequentially search the material design space (MDS) and identify parameters with the desired properties. At the heart of the intelligent control of these AEPs is the policy guiding the sequential experiments, which is to choose the location to carry out the next experiment. In such cases, a balance between exploitation and exploration must be achieved. A Bayesian Optimization (BO) framework with Expected Improvement based (EI-based) acquisition function can effectively search the MDS and guide where to conduct the next experiments so that the underlying relationship can be identified with a smaller number of experiments. The traditional BO framework tries to optimize a black box objective function in a sequential manner by relying on a single model. However, this single-model approach does not account for model uncertainty. Bayesian Model Averaging (BMA) addresses this issue by working with multiple models and thus considering the uncertainty in the models. In this work, we first apply the conventional BO algorithm with the most popular EI-based experiment policy in a real-life fatigue dataset for steel to predict the fatigue strength of steel. Afterward, we apply BMA to the same dataset by working with a set of predictive models and compare the performance of BMA with the traditional BO algorithm, which relies on a single model for approximation. We compare the results in terms of RMSE and find that BMA performs better than EI-based BO in the prediction task by considering the model uncertainty in its framework.