[Theory] NOW: [TTIC Talks] 9/29 Talks at TTIC: David Iseri Inouye, Purdue University

Brandie Jones bjones at ttic.edu
Fri Sep 29 10:29:01 CDT 2023


*When:*        Friday, September 29th at *10:30am CT*


*Where:       *Talk will be given *live, in-person* at

                       TTIC, 6045 S. Kenwood Avenue

                       5th Floor, Room 530


*Virtually:*  via Panopto (livestream
<https://uchicago.hosted.panopto.com/Panopto/Pages/Viewer.aspx?id=d64bd335-5220-4013-a0fe-b0810020e815>
)


*Who: *         David Iseri Inouye, Purdue University

*Title:*   Towards Trustworthy ML via Distribution Alignment
*Abstract:  *Distribution alignment has emerged as a cornerstone of
trustworthy machine learning, finding application in fairness, robustness,
causality, and explainability. Intuitively, distribution alignment is the
natural complement of classification: while classification labels define
what is important, alignment labels define what is not important. Although
substantial progress has been made by extending deep generative models such
as GANs, VAEs, flows, or diffusion models to distribution alignment,
research often remains fragmented, scattered across specific applications
and methods. By unifying alignment research along multiple dimensions, I
aim to provide a cohesive perspective, present ongoing work, and outline
future directions. Just as classification was the cornerstone of current
ML, the unification and advancement of distribution alignment could become
a critical tool for enabling the next generation of trustworthy ML.

*Bio:* Prof. David I. Inouye is an assistant professor in the Elmore Family
School of Electrical and Computer Engineering at Purdue University. His lab
focuses on trustworthy ML with a focus on distribution alignment, localized
learning, and explainable AI. Currently, he is interested in advancing
distribution alignment theory, algorithms, and applications such as
causality, domain generalization, and distribution shift explanations. He
is also interested in highly robust distributed learning algorithms on
networks of devices, called Internet Learning. His research is funded by
ARL, ONR, and NSF. Previously, he was a postdoc at Carnegie Mellon
University working with Prof. Pradeep Ravikumar. He completed his Computer
Science PhD at The University of Texas at Austin in 2017 advised by Prof.
Inderjit Dhillon and Prof. Pradeep Ravikumar. He was awarded the NSF
Graduate Research Fellowship (NSF GRFP).

*Host: **Saeed Sharifi-Malvajerdi <saeed at ttic.edu>*

--
*Brandie Jones *
*Executive **Administrative Assistant*
Toyota Technological Institute
6045 S. Kenwood Avenue
Chicago, IL  60637
www.ttic.edu
Working Remotely on Tuesdays
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mailman.cs.uchicago.edu/pipermail/theory/attachments/20230929/2a954138/attachment-0001.html>


More information about the Theory mailing list