Information Constrained Optimal Transport
Event details
Date | 06.07.2023 |
Hour | 11:00 › 12:00 |
Speaker | Prof. Ayfer Özgür |
Location | |
Category | Conferences - Seminars |
Event Language | English |
Optimal transport is the general problem of moving one distribution of mass to another as efficiently as possible. This problem has found a wealth of applications within mathematics as well as many other fields. In this talk, we will introduce an information constrained version of optimal transport and show that 1) it leads to the solution of an open problem in information theory formulated by Cover in 1987 which he calls the capacity of the relay channel; 2) it removes the curse of dimensionality in Wasserstein GANs and can be used to optimally train generative models from privatized data.
Prof. Ozgur is an associate professor in the Electrical Engineering Department of Stanford University and a member of ISL. Before joining Stanford, she was a postdoctoral researcher with the Algorithmic Research on Networked Information Group at EPFL, Switzerland. She received my PhD degree in October, 2009 from the Information Processing Group at the same university.
Prof. Ozgur is an associate professor in the Electrical Engineering Department of Stanford University and a member of ISL. Before joining Stanford, she was a postdoctoral researcher with the Algorithmic Research on Networked Information Group at EPFL, Switzerland. She received my PhD degree in October, 2009 from the Information Processing Group at the same university.
Practical information
- Informed public
- Free
Organizer
- IPG Seminar Prof. Emre Telatar
Contact
- Prof. Emre Telatar Mrs Muriel Bardet ([email protected])