BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Application of the optimal transport Gromov-Wasserstein problem to
  manifold learning and graph analysis - Hugues Van Assel\; École Normale 
 Supérieure de Lyon
DTSTART:20240613T100000Z
DTEND:20240613T110000Z
UID:TALK217963@talks.cam.ac.uk
CONTACT:Dr H Ge
DESCRIPTION:I will present some of my recent PhD research\, where we reexa
 mine unsupervised learning methods through the perspective of distribution
 s using optimal transport. By drawing connections with the Gromov-Wasserst
 ein (GW) problem\, this research introduces a new comprehensive framework 
 called distributional reduction. This framework encompasses both dimension
 ality reduction (DR) and clustering as special cases\, enabling to address
  them jointly within a single optimization problem. Additionally\, I will 
 discuss the applications of the GW problem as a similarity measure between
  structured data represented as distributions\, typically lying in differe
 nt metric spaces\, such as graphs of varying sizes. This will naturally le
 ad to exploring research directions in graph generative modeling using GW.
 \n\n\nShort biography:\n\nI studied at École Polytechnique and hold a res
 earch master's degree from École Normale Supérieure of Paris-Saclay. Cur
 rently\, I am a third-year PhD student in the mathematics department at É
 cole Normale Supérieure de Lyon\, supervised by Aurélien Garivier and Ti
 touan Vayer. I have completed several internships\, including positions at
  IBM Research Paris\, where I worked on time series forecasting\; Huawei N
 oah’s Ark Lab London\, focusing on model-based reinforcement learning wi
 th normalizing flows\; and Institut Pasteur\, where I researched variation
 al autoencoders (VAEs) for biosignals.
LOCATION:Cambridge University Engineering Department\, CBL Seminar room BE
 4-38.
END:VEVENT
END:VCALENDAR