[Theory] Talks at TTIC: 4/6 Mher Safaryan, King Abdullah University of Science and Technology

[Brandie Jones]

*When:*        Wednesday, April 6th at *9:30am CT*


*Where:*       *Zoom Virtual Talk* (*register in advance here*
<https://uchicago.zoom.us/meeting/register/tJYsdu-prD0tEtElhXgGda0xkL6_lCApz2jD>
)


*Who: *         Mher Safaryan, King Abdullah University of Science and
Technology

*Title:*           Communication-Efficient Distributed Optimization for
Machine Learning

*Abstract:    *In the quest for high accuracy machine learning models, both
the size of the model and consequently the amount of data necessary to
train the model have been hugely increased over time. Because of this,
performing the learning process on a single machine is often infeasible. In
a typical scenario of distributed learning, the training data is spread
across different machines, and thus the process of training is done in a
distributed manner. Another scenario, most common to federated learning, is
when training data is inherently distributed across a large number of
mobile edge devices due to data privacy concerns. Therefore, large-scale
distributed optimization has become the default tool for the training of
supervised machine learning models with a large number of parameters and
training data.

*Bio:  *Mher Safaryan is a postdoctoral fellow at King Abdullah University
of Science and Technology (KAUST) in Saudi Arabia, working on Optimization
for Machine Learning in the group supervised by Prof. Peter Richtárik.
Previously, he worked with Prof. Diogo Gomes as a research technician at
KAUST on Computer Algebra for Differential Equations. He did his Ph.D. in
Mathematics at Yerevan State University (YSU) in Armenia, under the
supervision of Prof. Grigori Karagulyan. His interests includes
optimization, machine learning, and compressed communication

*H**ost: Nathan Srebro <nati at ttic.edu>*


*Brandie Jones *
*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/20220404/55670ec1/attachment.html>