[Sds-seminars] [Sds-announce] Fwd: [FDS] 2/21 FDS Colloquium: “Learning from Data with Low-rank Priors and Beyond,” Dr. Yuejie Chi (CMU)

Tue Feb 20 20:07:31 EST 2024

Here's one more announcement of tomorrow's talk.
Note that there's a zoom link for those who can't attend in person.

  --Dan

---------- Forwarded message ---------
From: Hau, Emily <emily.hau at yale.edu>
Date: Tue, Feb 20, 2024 at 5:09 PM
Subject: [FDS] 2/21 FDS Colloquium: “Learning from Data with Low-rank
Priors and Beyond,” Dr. Yuejie Chi (CMU)
To: fds-announce at mailman.yale.edu <fds-announce at mailman.yale.edu>

FDS Colloquium: “Learning from Data with Low-rank Priors and Beyond,” Dr.
Yuejie Chi (CMU) *Speaker:* Dr. Yuejie Chi

*Sense of Wonder Group, Endowed Professor in AI Systems, Department of
Electrical and Computer Engineering, Machine Learning Department and CyLab
(by courtesy), Carnegie Mellon University*

*Wednesday, February 21, 2024*
*Lunch: 11:30 am (Kitchen)*
* Talk: 12:00 pm (Seminar Room #1327)*
at the Yale Institute for Foundations of Data Science, Kline Tower, 13th
Floor

*Also available via zoom:* https://yale.zoom.us/j/93063779957

Add To: Google Calendar
<https://calendar.google.com/calendar/r/eventedit?text=FDS+Colloquium%3A+%26%238220%3BLearning+from+Data+with+Low-rank+Priors+and+Beyond%2C%26%238221%3B+Dr.+Yuejie+Chi+%28CMU%29&details=Speaker%3A+Dr.+Yuejie+ChiSense+of+Wonder+Group%2C+Endowed+Professor+in+AI+Systems%2C+Department+of+Electrical+and+Computer+Engineering%2CMachine+Learning+Department+and+CyLab+%28by+courtesy%29%2CCarnegie+Mellon+University+Wednesday%2C+February+21%2C+2024Lunch%3A+11%3A30+am+%28Kitchen%29Talk%3A+12%3A00+pm+%28Seminar+Room+%231327%29at+the+Yale+institute+for+Foundations+of+Data+Science%2C+Kline+Tower%2C+13th+Floor+Title%3A+Learning+from+Data+with%26hellip%3B+%3Ca+class%3D%22continue%22+href%3D%22https%3A%2F%2Fcampuspress.yale.edu%2Ffds%2Fcalendar_event%2Ffds-colloquium-yuejie-chi%2F%22%3Econtinue+reading%3Cspan%3E+FDS+Colloquium%3A+%26%238220%3BLearning+from+Data+with+Low-rank+Priors+and+Beyond%2C%26%238221%3B+Dr.+Yuejie+Chi+%28CMU%29%3C%2Fspan%3E%3C%2Fa%3E...&location=Yale+Institute+for+Foundations+of+Data+Science%2C+Kline+Tower+13th+Floor%2C+Room+1327%2C+New+Haven%2C+CT+06511&dates=20240221T163000Z/20240221T180000Z>
 | Outlook
<https://campuspress.yale.edu/fds/wp-admin/admin-ajax.php?event=1504&action=download_ical_file>
 | iCal File
<https://campuspress.yale.edu/fds/wp-admin/admin-ajax.php?event=1504&action=download_ical_file>

*“**Learning from Data with Low-rank Priors and Beyond”*

*Abstract: *Generative priors are effective countermeasures to combat the
curse of dimensionality, and enable efficient learning and inversion that
otherwise are ill-posed, in data science. This talk begins with the
classical low-rank prior, and introduces scaled gradient descent
(ScaledGD), a simple iterative approach to directly recover the low-rank
factors for a wide range of matrix and tensor estimation tasks. ScaledGD
provably converges linearly at a constant rate independent of the condition
number at near-optimal sample complexities, while maintaining the low
per-iteration cost of vanilla gradient descent. In addition, ScaledGD
continues to admit fast global convergence from a small random
initialization when the rank is over-specified, confirming the benign
generalization of ScaledGD in learning overparameterized models. Going
beyond low rank, the talk discusses diffusion models as a promising data
prior in inverse problems, and highlights some ongoing efforts from
algorithmic foundations to applications in materials science.

*Bio: *Dr. Yuejie Chi is the Sense of Wonder Group Endowed Professor of
Electrical and Computer Engineering in AI Systems at Carnegie Mellon
University, with courtesy appointments in the Machine Learning department
and CyLab. She received her Ph.D. and M.A. from Princeton University, and
B. Eng. (Hon.) from Tsinghua University, all in Electrical Engineering. Her
research interests lie in the theoretical and algorithmic foundations of
data science, signal processing, machine learning and inverse problems,
with applications in sensing, imaging, decision making, and generative AI.
Among others, Dr. Chi is a recipient of the Presidential Early Career Award
for Scientists and Engineers (PECASE), the inaugural IEEE Signal Processing
Society Early Career Technical Achievement Award for contributions to
high-dimensional structured signal processing, and multiple paper awards
including the SIAM Activity Group on Imaging Science Best Paper Prize and
IEEE Signal Processing Society Young Author Best Paper Award. She is an
IEEE Fellow (Class of 2023) for contributions to statistical signal
processing with low-dimensional structures.

*Website:* https://users.ece.cmu.edu/~yuejiec/

*Upcoming Events:*

*Yale Theory Student Seminar: Max Ovsiankin (TTIC), “Approximation
Algorithms for lp-Shortest Path and lp-Network Design problems”
<https://fds.yale.edu/calendar_event/yale-theory-student-seminar-max-ovsiankin/>*

*On February 29, 2024 at 12:00 pm **Students only.*
  *Yale Theory Student Seminar: Geelon So (UCSD), “Optimization on Pareto
sets: Geometry of Multi-objective Optimization”
<https://fds.yale.edu/calendar_event/yale-theory-student-seminar-geelon-so/>*

*On March 5, 2024 at 12:00 pm **Students only.*
  *FDS Colloquium: Ankur Moitra (MIT) “Learning from Dynamics”
<https://fds.yale.edu/calendar_event/fds-colloquium-learning-from-dynamics-ankur-moitra-mit/>*

*On March 6, 2024 at 11:30 am*
  *Yale Theory Student Seminar: Siyu Chen, “Training Dynamics of Multi-Head
Softmax Attention for In-Context Learning: Emergence, Convergence, and
Optimality”
<https://fds.yale.edu/calendar_event/yale-theory-student-seminar-siyu-chen/>*

*On March 14, 2024 at 12:00 pm **Students only.*
  *S&DS Seminar: Johan Ugander (Stanford)
<https://fds.yale.edu/calendar_event/sds-seminar-johan-ugander-stanford/>*

*On March 25, 2024 at 3:30 pm*
  *FDS Colloquium: Aaditya Ramdas (CMU)
<https://fds.yale.edu/calendar_event/fds-colloquium-aaditya-ramdas/>*

*On March 27, 2024 at 11:30 am*
  *S&DS Seminar: Mingyuan Zhou (University of Texas at Austin)
<https://fds.yale.edu/calendar_event/sds-seminar-mingyuan-zhou-university-of-texas-at-austin/>*

*On April 1, 2024 at 4:00 pm*
  *FDS Colloquium: Lior Pachter (Caltech)
<https://fds.yale.edu/calendar_event/fds-colloquium-lior-pachter/>*

*On April 3, 2024 at 11:30 am*
  *S&DS Seminar: Santosh Vempala (Georgia Tech)
<https://fds.yale.edu/calendar_event/sds-seminar-santosh-vempala-georgia-tech/>*

*On April 8, 2024 at 4:00 pm*
  *S&DS Seminar: Yiling Chen (Harvard)
<https://fds.yale.edu/calendar_event/sds-seminar-yling-chen-harvard/>*

*On April 15, 2024 at 3:30 pm*
  *FDS Member Colloquium: Van Vu (Department of Mathematics)
<https://fds.yale.edu/calendar_event/fds-member-colloquium-van-vu/>*

*On April 17, 2024 at 11:30 am*
  *S&DS Seminar: Bingxin Zhao (UPenn)
<https://fds.yale.edu/calendar_event/fds-colloquium-bingxin-zhao/>*

*On April 22, 2024 at 3:30 pm*

*Workshop Honoring Andrew Barron: Forty Years at the Interplay of
Information Theory, Probability and Statistical Learning
<https://fds.yale.edu/calendar_event/workshop-honoring-andrew-barron/>*
*April 26-28, 2024*

Emily E. H. Hau | Associate Director
Yale Institute for Foundations of Data Science (FDS)
Yale University
US Mail: Kline Tower, P.O. Box 208328, New Haven CT 06520-8328
Courier: Kline Tower | 219 Prospect Street | Room 1333 | New Haven, CT 06511
emily.hau at yale.edu | P: 203-436-4732   @yaledatascience
<http://twitter.com/yaledatascience>
fds.yale.edu
-- 
Fds-announce mailing list
Fds-announce at mailman.yale.edu
Click on the URL to unsubscribe
https://mailman.yale.edu/mailman/listinfo/fds-announce
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mailman.yale.edu/pipermail/sds-seminars/attachments/20240220/01f99ad7/attachment.html>
-------------- next part --------------
A non-text attachment was scrubbed...
Name: image001.jpg
Type: image/jpeg
Size: 95750 bytes
Desc: not available
URL: <http://mailman.yale.edu/pipermail/sds-seminars/attachments/20240220/01f99ad7/attachment.jpg>
-------------- next part --------------
A non-text attachment was scrubbed...
Name: image004.jpg
Type: image/jpeg
Size: 10950 bytes
Desc: not available
URL: <http://mailman.yale.edu/pipermail/sds-seminars/attachments/20240220/01f99ad7/attachment-0001.jpg>
-------------- next part --------------
-- 
Sds-announce mailing list
Sds-announce at mailman.yale.edu
https://mailman.yale.edu/mailman/listinfo/sds-announce