BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Wasserstein Embeddings in the Deep Learning Era - Soheil  Kolouri 
  ()
DTSTART:20211124T170000Z
DTEND:20211124T183000Z
UID:TALK166237@talks.cam.ac.uk
DESCRIPTION:Computational optimal transport has found many applications in
  machine learning and\, more specifically\, deep learning as a fundamental
  tool to manipulate and compare probability distributions. The Wasserstein
  distances arising from the optimal transport problem have been of particu
 lar interest in recent years. However\, a consistent roadblock against the
  more prevalent use of transport-based methods has been their computationa
 l cost. Besides the more well-known ideas for faster computational approac
 hes\, including entropy regularization\, several fundamental concepts have
  emerged that enable the integration of transport-based methods as part of
  the computational graph of a deep neural network. Sliced-Wasserstein dist
 ances and the Linear Optimal Transport (LOT) framework are among fundament
 al concepts well suited for integration into today's deep neural networks.
  In this talk\, we will present the idea of Linear Optimal Transport (othe
 rwise known as the Wasserstein Embedding) and its extension to Sliced-Wass
 erstein Embeddings and demonstrate their various applications in deep lear
 ning with a particular interest in learning from graphs and set-structured
  data. The talk will be an overview of our recent ICLR 2021 and NeurIPS 20
 21 publications.
LOCATION:Seminar Room 2\, Newton Institute
END:VEVENT
END:VCALENDAR