Kernels over Sets of Finite Sets using RKHS Embeddings, with Application to Bayesian (Combinatorial) Optimization

Abstract : We focus on kernel methods for set-valued inputs and their application to Bayesian set optimization , notably combinatorial optimization. We introduce a class of (strictly) positive definite kernels that relies on Reproducing Kernel Hilbert Space embeddings, and successfully generalizes "double sum" set kernels recently considered in Bayesian set optimization , which turn out to be unsuitable for combinatorial optimization. The proposed class of kernels, for which we provide theoretical guarantees, essentially consists in applying an outer kernel on top of the canoni-cal distance induced by a double sum kernel. Proofs of theoretical results about considered kernels are complemented by a few practical-ities regarding hyperparameter fitting. We furthermore demonstrate the applicability of our approach in prediction and optimization tasks, relying both on toy examples and on two test cases from mechanical engineering and hydrogeology, respectively. Experimental results illustrate the added value of the approach and open new perspectives in prediction and sequential design with set inputs.
Complete list of metadatas

Cited literature [47 references]  Display  Hide  Download
Contributor : David Ginsbourger <>
Submitted on : Wednesday, October 9, 2019 - 3:13:07 PM
Last modification on : Thursday, October 10, 2019 - 1:11:23 AM


Files produced by the author(s)


  • HAL Id : hal-02309743, version 1



Poompol Buathong, David Ginsbourger, Tipaluck Krityakierne. Kernels over Sets of Finite Sets using RKHS Embeddings, with Application to Bayesian (Combinatorial) Optimization. 2019. ⟨hal-02309743⟩



Record views


Files downloads