Determinantal point processes in the flat limit

被引:1
|
作者
Barthelme, Simon [1 ]
Tremblay, Nicolas [1 ]
Usevich, Konstantin [2 ,3 ]
Amblard, Pierre-Olivier [1 ]
机构
[1] Univ Grenoble Alpes, Grenoble INP, GIPSA Lab, CNRS, Grenoble, France
[2] Univ Lorraine, Grenoble, France
[3] CRAN Ctr Rech Automat Nancy, CNRS, Grenoble, France
关键词
Determinantal point processes; kernel methods; flat limit; INTERPOLATION;
D O I
10.3150/22-BEJ1486
中图分类号
O21 [概率论与数理统计]; C8 [统计学];
学科分类号
020208 ; 070103 ; 0714 ;
摘要
Determinantal point processes (DPPs) are repulsive point processes where the interaction between points depends on the determinant of a positive-semi definite matrix. In this paper, we study the limiting process of L-ensembles based on kernel matrices, when the kernel function becomes flat (so that every point interacts with every other point, in a sense). We show that these limiting processes are best described in the formalism of extended L-ensembles and partial projection DPPs, and the exact limit depends mostly on the smoothness of the kernel function. In some cases, the limiting process is even universal, meaning that it does not depend on specifics of the kernel function, but only on its degree of smoothness. Since flat-limit DPPs are still repulsive processes, this implies that practically useful families of DPPs exist that do not require a spatial length-scale parameter.
引用
收藏
页码:957 / 983
页数:27
相关论文
共 50 条
  • [41] Orbit measures and interlaced determinantal point processes
    Defosseux, Manon
    COMPTES RENDUS MATHEMATIQUE, 2008, 346 (13-14) : 783 - 788
  • [42] A note on tail triviality for determinantal point processes
    Lyons, Russell
    ELECTRONIC COMMUNICATIONS IN PROBABILITY, 2018, 23
  • [43] Large-Margin Determinantal Point Processes
    Chao, Wei-Lun
    Gong, Boqing
    Grauman, Kristen
    Sha, Fei
    UNCERTAINTY IN ARTIFICIAL INTELLIGENCE, 2015, : 191 - 200
  • [44] Fast Dynamic Sampling for Determinantal Point Processes
    Song, Zhao
    Yin, Junze
    Zhang, Lichen
    Zhang, Ruizhe
    INTERNATIONAL CONFERENCE ON ARTIFICIAL INTELLIGENCE AND STATISTICS, VOL 238, 2024, 238
  • [45] Learning Determinantal Point Processes in Sublinear Time
    Dupuy, Christophe
    Bach, Francis
    INTERNATIONAL CONFERENCE ON ARTIFICIAL INTELLIGENCE AND STATISTICS, VOL 84, 2018, 84
  • [46] Individualness and Determinantal Point Processes for Pedestrian Detection
    Lee, Donghoon
    Cha, Geonho
    Yang, Ming-Hsuan
    Oh, Songhwai
    COMPUTER VISION - ECCV 2016, PT VI, 2016, 9910 : 330 - 346
  • [47] Markov Properties of Discrete Determinantal Point Processes
    Sadeghi, Kayvan
    Rinaldo, Alessandro
    22ND INTERNATIONAL CONFERENCE ON ARTIFICIAL INTELLIGENCE AND STATISTICS, VOL 89, 2019, 89
  • [48] Conditional Intensity and Gibbsianness of Determinantal Point Processes
    Hans-Otto Georgii
    Hyun Jae Yoo
    Journal of Statistical Physics, 2005, 118 : 55 - 84
  • [49] RANDOM STRICT PARTITIONS AND DETERMINANTAL POINT PROCESSES
    Petrov, Leonid
    ELECTRONIC COMMUNICATIONS IN PROBABILITY, 2010, 15 : 162 - 175
  • [50] Clustering Ensemble Selection with Determinantal Point Processes
    Liu, Wei
    Yue, Xiaodong
    Zhong, Caiming
    Zhou, Jie
    NEURAL INFORMATION PROCESSING (ICONIP 2019), PT III, 2019, 11955 : 621 - 633