BCAST template email
by Marcin Chrapek
SPCL_Bcast Virginia Smith
The Scalable Parallel Computing Lab's *SPCL_Bcast* seminar continues
with *Virginia Smith of CMU* presenting on *Evaluating Large-Scale
Learning Systems*. Everyone is welcome to attend (over Zoom)!
When: Thursday, 28th September, 6PM CET
Where: Zoom
Join <https://spcl.inf.ethz.ch/Bcast/join>
Abstract: To deploy machine learning models in practice it is critical
to have a way to reliably evaluate their effectiveness. Unfortunately,
the scale and complexity of modern machine learning systems makes it
difficult to provide faithful evaluations and gauge performance across
potential deployment scenarios. In this talk I discuss our work
addressing challenges in large-scale ML evaluation. First, I explore the
problem of evaluating models trained in federated networks of devices,
where issues of device subsampling, heterogeneity, and privacy can
introduce noise in the evaluation process and make it challenging to
provide reliable evaluations. Second, I present ReLM, a system for
validating and querying large language models (LLMs). Although LLMs have
been touted for their ability to generate natural-sounding text, there
is a growing need to evaluate the behavior of LLMs in light of issues
such as data memorization, bias, and inappropriate language. ReLM poses
LLM validation queries as regular expressions to enable faster and more
effective LLM evaluation.
Biography: Virginia Smith is an assistant professor in the Machine
Learning Department at Carnegie Mellon University. Her research spans
machine learning, optimization, and distributed systems. Virginia’s
current work addresses challenges related to optimization, privacy, and
robustness in distributed settings to enable trustworthy federated
learning at scale. Virginia’s work has been recognized by an NSF CAREER
Award, MIT TR35 Innovator Award, Intel Rising Star Award, and faculty
awards from Google, Apple, and Meta. Prior to CMU, Virginia was a
postdoc at Stanford University and received a Ph.D. in Computer Science
from UC Berkeley.
More details & future talks <https://spcl.inf.ethz.ch/Bcast/>
Scalable Parallel Computing Lab (SPCL)
Department of Computer Science, ETH Zurich
Website, Twitter, Youtube, Github
7 months, 1 week
New team member – Patrik Okanovic
by Torsten Hoefler
Hi Team,
On October 2nd a new group member will join us – Patrik Okanovic.
Patrik is joining us as a PhD student. Lukas will bring him around on
his first day to say hello and meet everyone.
I wish you all a nice day, and inspiration for your work!
Best,
Torsten
--
### qreharg rug ebs fv crryF --- http://htor.inf.ethz.ch/ ---
Torsten Hoefler | Professor
Dept. of Computer Science | ETH Zürich
Universitätsstrasse 6 | Zurich-8092, Switzerland
CAB F 75 | Phone: +41 44 632 68 79
7 months, 1 week
New team member – Luigi Fusco
by Torsten Hoefler
Hi Team,
On September 25th, a new group member will join us – Luigi Fusco.
Luigi is joining us as a PhD student. Tommaso will bring him around on
Monday to say hello and meet everyone.
I wish you all a nice day, and inspiration for your work!
Best,
Torsten
--
### qreharg rug ebs fv crryF --- http://htor.inf.ethz.ch/ ---
Torsten Hoefler | Professor
Dept. of Computer Science | ETH Zürich
Universitätsstrasse 6 | Zurich-8092, Switzerland
CAB F 75 | Phone: +41 44 632 68 79
7 months, 1 week
New group member: Benjamin Weber
by Torsten Hoefler
Hi SPCLists,
On September 11th a new group member joined us – Benjamin Weber. (sorry
for my delay, was a temporary overload)
Benjamin is joining us as Software Development Project lead and by now,
I hope you talked to him. Please make him feel welcome and engage him in
group activities.
I wish you all a nice day, and inspiration for your work!
Best,
Torsten
--
### qreharg rug ebs fv crryF ---http://htor.inf.ethz.ch/ ---
Torsten Hoefler | Professor
Dept. of Computer Science | ETH Zürich
Universitätsstrasse 6 | Zurich-8092, Switzerland
CAB F 75 | Phone: +41 44 632 68 79
7 months, 2 weeks
