Learning the Parameters of Determinantal Point Process Kernels

TL;DR

This paper introduces Bayesian methods for learning the parameters of DPP kernels, enabling scalable and effective modeling of diversity in large-scale and continuous settings, with applications in medical imaging and perception studies.

Contribution

It proposes novel Bayesian approaches for DPP kernel parameter estimation applicable to large-scale and continuous data, overcoming non-convex likelihood challenges.

Findings

Effective DPP parameter learning in large-scale settings

Application to diabetic neuropathy progression analysis

Study of human perception of image diversity

Abstract

Determinantal point processes (DPPs) are well-suited for modeling repulsion and have proven useful in many applications where diversity is desired. While DPPs have many appealing properties, such as efficient sampling, learning the parameters of a DPP is still considered a difficult problem due to the non-convex nature of the likelihood function. In this paper, we propose using Bayesian methods to learn the DPP kernel parameters. These methods are applicable in large-scale and continuous DPP settings even when the exact form of the eigendecomposition is unknown. We demonstrate the utility of our DPP learning methods in studying the progression of diabetic neuropathy based on spatial distribution of nerve fibers, and in studying human perception of diversity in images.