aiqbench analysis
This research introduces a "joint contour location" framework for simultaneously identifying input configurations that satisfy multiple response constraints across computer experiments. By employing Gaussian processes and deep GPs with distinct acquisition schemes, the method efficiently balances exploration and exploitation to locate optimal conditions, such as stable flight states with zero torque. The approach significantly outperforms existing single-response strategies, offering a robust tool for complex multi-objective optimization in scientific computing.
Actively Learning Joint Contours of Multiple Computer Experiments
arXiv:2512.13530v2 Announce Type: replace-cross Abstract: Contour location---the process of sequentially training a surrogate model to identify the design inputs that result in a pre-specified response value from a single computer experiment---is a well-studied active learning problem. Here, we tackle a related but distinct problem: identifying the input configuration that returns pre-specified values of multiple computer experiments simultaneously. Motivated by computer experiments of the rotational torques acting upon a vehicle in flight, we aim to identify stable flight conditions that result in zero torque forces. We propose a ``joint contour location'' (jCL) scheme that strikes a strategic balance between exploring the multiple response surfaces while exploiting learning of the intersecting contours. Rather than working exploration and exploitation into a single acquisition function, we devise two distinct acquisition schemes with a decision rule to choose between the two, which also provides a natural stopping criterion if no solution is present. We employ traditional Gaussian processes (GPs), multitask GPs, and deep GPs, but our jCL procedure is applicable to any surrogate that can provide posterior predictive distributions. Our jCL designs significantly outperform existing (single response) CL strategies, optimization-based alternatives, and previous strategies for targeting joint contours, enabling us to efficiently locate the optimal configurations for our motivating computer experiments.
Abstract:Contour location---the process of sequentially training a surrogate model to identify the design inputs that result in a pre-specified response value from a single computer experiment---is a well-studied active learning problem. Here, we tackle a related but distinct problem: identifying the input configuration that returns pre-specified values of multiple computer experiments simultaneously. Motivated by computer experiments of the rotational torques acting upon a vehicle in flight, we aim to identify stable flight conditions that result in zero torque forces. We propose a ``joint contour location'' (jCL) scheme that strikes a strategic balance between exploring the multiple response surfaces while exploiting learning of the intersecting contours. Rather than working exploration and exploitation into a single acquisition function, we devise two distinct acquisition schemes with a decision rule to choose between the two, which also provides a natural stopping criterion if no solution is present. We employ traditional Gaussian processes (GPs), multitask GPs, and deep GPs, but our jCL procedure is applicable to any surrogate that can provide posterior predictive distributions. Our jCL designs significantly outperform existing (single response) CL strategies, optimization-based alternatives, and previous strategies for targeting joint contours, enabling us to efficiently locate the optimal configurations for our motivating computer experiments.
Methodology (stat.ME); Machine Learning (cs.LG)
arXiv:2512.13530 [stat.ME]
(or arXiv:2512.13530v2 [stat.ME] for this version)
https://doi.org/10.48550/arXiv.2512.13530 Focus to learn more arXiv-issued DOI via DataCite
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 295 words
