Active learning for directed exploration of complex systems

Abstract

Physics-based simulation codes are widely used in science and engineering to model complex systems that would be infeasible to study otherwise. Such codes provide the highest-fidelity representation of system behavior, but are often so slow to run that insight into the system is limited. For example, conducting an exhaustive sweep over a d-dimensional input parameter space with ksteps along each dimension requires k d simulation trials (translating into k d CPU-days for one of our current simulations). An alternative is directed exploration in which the next simulation trials are cleverly chosen at each step. Given the results of previous trials, supervised learning techniques (SVM, KDE, GP) are applied to build up simplified predictive models of system behavior. These models are then used within an active learning framework to identify the most valuable trials to run next. Several active learning strategies are examined including a recently-proposed information-theoretic approach. Performance is evaluated on a set of thirteen synthetic oracles, which serve as surrogates for the more expensive simulations and enable the experiments to be replicated by other researchers.

Batch Mode Active Learning for Multimedia Pattern Recognition

“…Wiens and Guttag [201] applied active learning algorithms to perform patient-adaptive and task-adaptive heartbeat classification. Burl and Wang [202] applied active learning to study the behavior of complex systems using physics based simulation codes. However, all these approaches have been based on serial query strategies; we now review existing work on batch mode active learning, which is the primary focus of this thesis.…”