En poursuivant votre navigation sur ce site, vous acceptez l'utilisation d'un simple cookie d'identification. Aucune autre exploitation n'est faite de ce cookie. OK
1

Gradient flows for sampling and their deterministic interacting particle approximations

Bookmarks Report an error
Multi angle
Authors : Slepčev, Dejan (Author of the conference)
CIRM (Publisher )

Loading the player...

Abstract : Motivated by the task of sampling measures in high dimensions we will discuss a number of gradient flows in the spaces of measures, including the Wasserstein gradient flows of Maximum Mean Discrepancy and Hellinger gradient flows of relative entropy, the Stein Variational Gradient Descent and a new projected dynamic gradient flows. For all the flows we will consider their deterministic interacting-particle approximations. The talk is highlight some of the properties of the flows and indicate their differences. In particular we will discuss how well can the interacting particles approximate the target measures.The talk is based on joint works wit Anna Korba, Lantian Xu, Sangmin Park, Yulong Lu, and Lihan Wang.

Keywords : Gradient flow; sampling; nonlocal equations; interacting particle systems

MSC Codes :
45M05 - Asymptotics
62D05 - Sampling theory, sample surveys
82C21 - Dynamic continuum models (systems of particles, etc.)
35Q70 - PDEs in connection with mechanics of particles and systems
35Q62 - PDEs in connection with statistics

Additional resources :
https://www.cirm-math.fr/RepOrga/3049/Slides/Dejan_Slepcev_CIRM.pdf

    Information on the Video

    Film maker : Hennenfent, Guillaume
    Language : English
    Available date : 30/04/2024
    Conference Date : 11/04/2024
    Subseries : Research talks
    arXiv category : Analysis of PDEs
    Mathematical Area(s) : Analysis and its Applications ; Numerical Analysis & Scientific Computing ; PDE
    Format : MP4 (.mp4) - HD
    Video Time : 00:48:23
    Targeted Audience : Researchers ; Graduate Students ; Doctoral Students, Post-Doctoral Students
    Download : https://videos.cirm-math.fr/2024-04-11_Slepcev.mp4

Information on the Event

Event Title : Aggregation-Diffusion Equations & Collective Behavior: Analysis, Numerics and Applications / Conférence Chaire Jean Morlet: Equations d'agrégation-diffusion et comportement collectif: Analyse, schémas numériques et applications
Event Organizers : Carrillo, José Antonio ; Esposito, Antonio ; Gómez-Castro, David ; Nouri, Anne
Dates : 08/04/2024 - 12/04/2024
Event Year : 2024
Event URL : https://conferences.cirm-math.fr/3049.html

Citation Data

DOI : 10.24350/CIRM.V.20160203
Cite this video as: Slepčev, Dejan (2024). Gradient flows for sampling and their deterministic interacting particle approximations. CIRM. Audiovisual resource. doi:10.24350/CIRM.V.20160203
URI : http://dx.doi.org/10.24350/CIRM.V.20160203

See Also

Bibliography

  • LU, Yulong, SLEPČEV, Dejan, et WANG, Lihan. Birth–death dynamics for sampling: global convergence, approximations and their asymptotics. Nonlinearity, 2023, vol. 36, no 11, p. 5731. - http://dx.doi.org/10.1088/1361-6544/acf988

  • PARK, Sangmin et SLEPČEV, Dejan. Geometry and analytic properties of the sliced Wasserstein space. arXiv preprint arXiv:2311.05134, 2023. - https://arxiv.org/abs/2311.05134

  • XU, Lantian, KORBA, Anna, et SLEPCEV, Dejan. Accurate quantization of measures via interacting particle-based optimization. In : International Conference on Machine Learning. PMLR, 2022. p. 24576-24595. - https://proceedings.mlr.press/v162/xu22d.html



Imagette Video

Bookmarks Report an error