Global Optimization Networks

Sen Zhao · Erez Louidor · Maya Gupta

Hall E #707

Keywords: [ OPT: Global Optimization ] [ SA: Accountability, Transparency and Interpretability ] [ SA: Trustworthy Machine Learning ] [ DL: Everything Else ] [ OPT: Learning for Optimization ]

[ Abstract ]
[ Poster [ Paper PDF
Thu 21 Jul 3 p.m. PDT — 5 p.m. PDT
Spotlight presentation: Optimization/Probabilistic Methods
Thu 21 Jul 12:30 p.m. PDT — 2 p.m. PDT

Abstract: We consider the problem of estimating a good maximizer of a black-box function given noisy examples. We propose to fit a new type of function called a global optimization network (GON), defined as any composition of an invertible function and a unimodal function, whose unique global maximizer can be inferred in $\mathcal{O}(D)$ time, and used as the estimate. As an example way to construct GON functions, and interesting in its own right, we give new results for specifying multi-dimensional unimodal functions using lattice models with linear inequality constraints. We extend to \emph{conditional} GONs that find a global maximizer conditioned on specified inputs of other dimensions. Experiments show the GON maximizers are statistically significantly better predictions than those produced by convex fits, GPR, or DNNs, and form more reasonable predictions for real-world problems.

Chat is not available.