[Colloquium] REMINDER: 5/18 Machine Learning Seminar Series: Jonathan Weed, MIT

[Mary Marre via Colloquium]

 When:     Friday, May 18th at *11:00 am*

Where:    TTIC, 6045 S Kenwood Avenue, 5th Floor, Room 526

Who:       Jonathan Weed, MIT


Title: Near-Linear Time Approximation Algorithms for Optimal Transport

Abstract: Computing optimal transport distances between distributions is a
fundamental problem that is becoming increasingly prominent in statistics,
image processing, and machine learning. Key to the use of optimal transport
in practice is the existence of fast, stable algorithms for computing these
distances. In this work, we exhibit a simple approximation algorithm for
this problem that runs in near-linear time. Our work is based on new
analysis of the celebrated Sinkhorn algorithm for matrix scaling, as well
as new results about the behavior of linear programs under entropic
penalization. Joint work with Jason Altschuler and Philippe Rigollet.



For more information on the *Machine Learning Seminar Series* (MLSS), please
request to join the group at https://groups.google.com/a/ttic.edu/d/forum/
mlss. If you are interested in presenting in the seminar, please send an
email to suriya at ttic.edu.




Mary C. Marre
Administrative Assistant
*Toyota Technological Institute*
*6045 S. Kenwood Avenue*
*Room 504*
*Chicago, IL  60637*
*p:(773) 834-1757*
*f: (773) 357-6970*
*mmarre at ttic.edu <mmarre at ttic.edu>*

On Wed, May 16, 2018 at 2:47 PM, Mary Marre <mmarre at ttic.edu> wrote:

> When:     Friday, May 18th at *11:00 am*
>
> Where:    TTIC, 6045 S Kenwood Avenue, 5th Floor, Room 526
>
> Who:       Jonathan Weed, MIT
>
>
> Title: Near-Linear Time Approximation Algorithms for Optimal Transport
>
> Abstract: Computing optimal transport distances between distributions is a
> fundamental problem that is becoming increasingly prominent in statistics,
> image processing, and machine learning. Key to the use of optimal transport
> in practice is the existence of fast, stable algorithms for computing these
> distances. In this work, we exhibit a simple approximation algorithm for
> this problem that runs in near-linear time. Our work is based on new
> analysis of the celebrated Sinkhorn algorithm for matrix scaling, as well
> as new results about the behavior of linear programs under entropic
> penalization. Joint work with Jason Altschuler and Philippe Rigollet.
>
>
>
> For more information on the *Machine Learning Seminar Series* (MLSS), please
> request to join the group at https://groups.google.com/a/ttic.edu/d/forum/
> mlss. If you are interested in presenting in the seminar, please send an
> email to suriya at ttic.edu.
>
>
>
>
>
> Mary C. Marre
> Administrative Assistant
> *Toyota Technological Institute*
> *6045 S. Kenwood Avenue*
> *Room 504*
> *Chicago, IL  60637*
> *p:(773) 834-1757*
> *f: (773) 357-6970*
> *mmarre at ttic.edu <mmarre at ttic.edu>*
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mailman.cs.uchicago.edu/pipermail/colloquium/attachments/20180517/4d8bc5a7/attachment-0001.html>