A Faster Sampler for Discrete Determinantal Point Processes - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2023

A Faster Sampler for Discrete Determinantal Point Processes

Résumé

Discrete Determinantal Point Processes (DPPs) have a wide array of potential applications for subsampling datasets. They are however held back in some cases by the high cost of sampling. In the worst-case scenario, the sampling cost scales as O(n^3) where n is the number of elements of the ground set. A popular workaround to this prohibitive cost is to sample DPPs defined by low-rank kernels. In such cases, the cost of standard sampling algorithms scales as O(np^2 + nm^2) where m is the (average) number of samples of the DPP (usually m << n) and p the rank of the kernel used to define the DPP (m \leq p \leq n). The first term, O(np^2), comes from a SVD-like step. We focus here on the second term of this cost, O(nm^2), and show that it can be brought down to O(nm + m^3 log m) without loss on the sampling's exactness. In practice, we observe very substantial speedups compared to the classical algorithm as soon as n > 1000. The algorithm described here is a close variant of the standard algorithm for sampling continuous DPPs, and uses rejection sampling. In the specific case of projection DPPs, we also show that any additional sample can be drawn in time O(m^3 log m).Finally, an interesting by-product of the analysis is that a realisation from a DPP is typically contained in a subset of size O(m log m) formed using leverage score i.i.d. sampling.
Fichier principal
Vignette du fichier
main.pdf (532.21 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03835312 , version 1 (31-10-2022)
hal-03835312 , version 2 (22-02-2023)

Identifiants

Citer

Simon Barthelme, Nicolas Tremblay, Pierre-Olivier Amblard. A Faster Sampler for Discrete Determinantal Point Processes. AISTATS 2023 - 26th International Conference on Artificial Intelligence and Statistics, Apr 2023, Valencia, Spain. pp.5582-5592. ⟨hal-03835312v2⟩
32 Consultations
33 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More