We cordially invite you to participate in the upcoming IEEE Workshop on Seeking Low-dimensionality in Deep Neural Networks (SLowDNN), Nov. 23rd – 24th, 2020.

https://sites.google.com/view/slowdnn/

This two-day workshop aims to bring together experts in machine learning, applied mathematics, signal processing, and optimization, and to share recent progress and foster collaborations on mathematical foundations of deep learning. We would like to stimulate vibrate discussions towards bridging the gap between the theory and practice of deep learning by developing more principled and unified mathematical framework based on the theory and methods for learning low-dimensional models in high-dimensional space.

The workshop is technically sponsored by the IEEE Computational Imaging Technical Committee (CI TC), and is co-sponsored by Mathematical Institute for Data Science at JHU and Georgen Institute for Data Science at University of Rochester.

We have a stellar line of invited speakers (alphabetical order):

– Yuejie Chi (CMU, ECE)

– Alex Dimakis (UT Austin, ECE)

– Carlos Fernandez-Granda (NYU Courant & CDS)

– Tom Goldstein (UMD, CS)

– Boris Hanin (Princeton, ORFE)

– Yi Ma (UC Berkeley, EECS)

– Ruoyu Sun (UIUC, ISE)

– Rene Vidal (JHU, MINDS & BME)

– John Wright (Columbia U, EE & DSI)

– Jong Chul Ye (KAIST)

Besides, we will host a panel discussion and a “young research spotlight” session at the end of each day.

The workshop will be held on Zoom. Registration (link on homepage) will be free, and the Zoom links will be sent to registered participants.

Best Regards,

The Organizer Team (Qing, Jeremias, Atlas, Zhihui, Chong, and Yi)