Bayesian Optimization on Networks
By: Wenwen Li, Daniel Sanz-Alonso, Ruiyi Yang
Potential Business Impact:
Finds best spots on maps for tough problems.
This paper studies optimization on networks modeled as metric graphs. Motivated by applications where the objective function is expensive to evaluate or only available as a black box, we develop Bayesian optimization algorithms that sequentially update a Gaussian process surrogate model of the objective to guide the acquisition of query points. To ensure that the surrogates are tailored to the network's geometry, we adopt Whittle-Mat\'ern Gaussian process prior models defined via stochastic partial differential equations on metric graphs. In addition to establishing regret bounds for optimizing sufficiently smooth objective functions, we analyze the practical case in which the smoothness of the objective is unknown and the Whittle-Mat\'ern prior is represented using finite elements. Numerical results demonstrate the effectiveness of our algorithms for optimizing benchmark objective functions on a synthetic metric graph and for Bayesian inversion via maximum a posteriori estimation on a telecommunication network.
Similar Papers
Global Optimization on Graph-Structured Data via Gaussian Processes with Spectral Representations
Machine Learning (CS)
Finds best patterns in connected data faster.
Towards Scalable Bayesian Optimization via Gradient-Informed Bayesian Neural Networks
Machine Learning (CS)
Makes computer learning faster by using more math.
Risk-aware black-box portfolio construction using Bayesian optimization with adaptive weighted Lagrangian estimator
Machine Learning (CS)
Helps money managers pick safer, better investments.