[Colloquium] REMINDER: 2/4 Talks at TTIC: Jonathan Weed, MIT

Mary Marre via Colloquium colloquium at mailman.cs.uchicago.edu
Mon Feb 4 10:25:12 CST 2019


When:     Monday, February 4th at *11:00 am*

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

Who:       Jonathan Weed, MIT


*Title:       *Statistical Optimal Transport via Regularized Couplings

*Abstract:* Optimal transport is a tool from probability theory which has
recently seen a surge of interest in machine learning for tasks such as
domain adaptation and integrative data analysis. However, successfully
employing optimal transport for ML problems in practice requires
introducing the right inductive bias. In this talk, we introduce three
different regularization techniques designed to improve the performance of
optimal transport for large-scale empirical data.

Host: Nathan Srebro <nati at ttic.edu>


Mary C. Marre
Administrative Assistant
*Toyota Technological Institute*
*6045 S. Kenwood Avenue*
*Room 517*
*Chicago, IL  60637*
*p:(773) 834-1757*
*f: (773) 357-6970*
*mmarre at ttic.edu <mmarre at ttic.edu>*


On Sun, Feb 3, 2019 at 7:01 PM Mary Marre <mmarre at ttic.edu> wrote:

> When:     Monday, February 4th at *11:00 am*
>
> Where:    TTIC, 6045 S Kenwood Avenue, 5th Floor, Room 526
>
> Who:       Jonathan Weed, MIT
>
>
> *Title:       *Statistical Optimal Transport via Regularized Couplings
>
> *Abstract:* Optimal transport is a tool from probability theory which has
> recently seen a surge of interest in machine learning for tasks such as
> domain adaptation and integrative data analysis. However, successfully
> employing optimal transport for ML problems in practice requires
> introducing the right inductive bias. In this talk, we introduce three
> different regularization techniques designed to improve the performance of
> optimal transport for large-scale empirical data.
>
> Host: Nathan Srebro <nati at ttic.edu>
>
>
> Mary C. Marre
> Administrative Assistant
> *Toyota Technological Institute*
> *6045 S. Kenwood Avenue*
> *Room 517*
> *Chicago, IL  60637*
> *p:(773) 834-1757*
> *f: (773) 357-6970*
> *mmarre at ttic.edu <mmarre at ttic.edu>*
>
>
> On Mon, Jan 28, 2019 at 6:39 PM Mary Marre <mmarre at ttic.edu> wrote:
>
>> When:     Monday, February 4th at *11:00 am*
>>
>> Where:    TTIC, 6045 S Kenwood Avenue, 5th Floor, Room 526
>>
>> Who:       Jonathan Weed, MIT
>>
>>
>> *Title:       *Statistical Optimal Transport via Regularized Couplings
>>
>> *Abstract:* Optimal transport is a tool from probability theory which
>> has recently seen a surge of interest in machine learning for tasks such as
>> domain adaptation and integrative data analysis. However, successfully
>> employing optimal transport for ML problems in practice requires
>> introducing the right inductive bias. In this talk, we introduce three
>> different regularization techniques designed to improve the performance of
>> optimal transport for large-scale empirical data.
>>
>> Host: Nathan Srebro <nati at ttic.edu>
>>
>>
>>
>> Mary C. Marre
>> Administrative Assistant
>> *Toyota Technological Institute*
>> *6045 S. Kenwood Avenue*
>> *Room 517*
>> *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/20190204/a682e837/attachment-0001.html>


More information about the Colloquium mailing list