[Theory] [Talks at TTIC] 4/14 TTIC Colloquium:​Samory K. Kpotufe​, Columbia University

[Brandie Jones via Theory]

*When:*        Monday, April 14th at *11:30am 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=bb0b2b08-d31b-44f7-80e4-b29e01084eee>
)


*Who: *         Samory K. Kpotufe, Columbia University

*Title:*          A more Unified Theory of Transfer Learning
*Abstract:  *Transfer Learning aims to leverage samples from different but
related distributions to improve performance on a target task. In its
simplest form, one aims to optimally aggregate data from one source
distribution with data from the target task. Multiple procedures have been
proposed over the last decade to address this problem, each driven by one
of many possible divergence measures between source and target
distributions. We ask whether there exist unified algorithmic approaches
that automatically adapt to many of these divergence measures
simultaneously.

We show that this is indeed the case for a large family of divergences
proposed across classification and regression problems: these divergences
all happen to upper-bound the same measures of continuity between source
and target risks, which we refer to as "moduli of transfer", hence reducing
the algorithmic question to that of adapting to these moduli. This more
unified view allows us, first, to identify algorithmic approaches that are
simultaneously adaptive to these various divergence measures—via a
reduction to certain types of confidence set. Second, it allows for a more
refined understanding of the statistical limits of transfer under such
divergences, and in particular, reveals regimes with faster rates than
might be expected under coarser lenses.

The talk is based on joint work with collaborators over the last few years,
namely, S. Hanneke, and also M. Kalan, N. Galbraith, Y. Mahdaviyeh, G.
Martinet, , J. Suk, Y. Deng.

*Short Bio*: Samory Kpotufe is Professor of Statistics at Columbia
University and works primarily on statistical machine learning theory. He
has held previous faculty and research appointments at Princeton
University, ORFE, and at TTI Chicago. Prior to this, he graduated in 2010
from UC San Diego, CS, advised by S. Dasgupta, followed by postdoctoral
research at the Max Planck Institute, Tuebingen, Germany. Notable awards
include a Bell Labs First prize 2019, a Sloan Fellowship in 2021, and paper
awards from machine learning venues including COLT and NeuRIPS.


*Host: Avrim Blum <avrim at ttic.edu>*

-- 
*Brandie Jones *
*Executive **Administrative Assistant*
Toyota Technological Institute
6045 S. Kenwood Avenue
Chicago, IL  60637
www.ttic.edu
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mailman.cs.uchicago.edu/pipermail/theory/attachments/20250407/790cb3a6/attachment.html>