Join Us in Abu Dhabi from 3-7 January 2023!
Video Recordings from the Workshop
Announcing the workshop venue: W Abu Dhabi Hotel at Yas Island (Google Maps)
Register here for in-person and remote participation
Key Dates and Deadlines
- Workshop dates: 3rd - 7th January, 2023; in person at W Hotel, Abu Dhabi
- Submission portal opens: October 1st, 2022
- Paper submission deadline: November 6th, 2022
- Acceptance and travel grant notification: November 20th, 2022
The top accepted papers will be recommended for inclusion in a future special issue of the IEEE Journal of Selected Topics in Signal Processing.
Workshop Themes
In the past decade, deep learning has demonstrated unprecedented performance across many different domains. Modern neural networks learn high-performing nonlinear representations for complex multi-modal data (e.g. text and image) without labels; they generate near-photorealistic high-resolution images from random noise; and they efficiently reconstruct data from compressive, corrupted measurements in various imaging and structural prediction tasks.
However, despite recent endeavors, the underlying principles behind their success remain shrouded in mystery. At a fundamental level, each of these successes, and numerous others in scientific and engineering applications, stem from the low-dimensional structure present both in the training data and in the networks themselves. This presents a significant opportunity to bring insights from better-understood low-dimensional models to the setting of deep learning, where models are notoriously plagued by issues of poor resource and data efficiency, robustness, and generalization.
Given these exciting but relatively less-exploited connections, this workshop aims to bring together experts in machine learning, applied mathematics, signal processing, and optimization, to share recent progress and foster collaborations on the mathematical foundations of deep learning. As the community continues to embrace the power of deep learning, with unprecedented new challenges in terms of modeling and interpretability, we hope to stimulate vibrant discussions towards bridging the gap between the theory and practice of deep learning, with low-dimensionality as a unifying focus.
Confirmed Speakers
Information on the speakers’ planned talks is available here.
Misha Belkin
UC San Diego
Beidi Chen
Meta
Ivan Dokmanić
University of Basel
Simon Du
University of Washington
Reinhard Heckel
TU Munich
Gitta Kutyniok
LMU Munich
Jason Lee
Princeton
Qi Lei
NYU
Yi Ma
UC Berkeley
Rina Panigrahy
Qing Qu
UMich
Ohad Shamir
Weizmann Institute
Daniel Soudry
Technion
Weijie Su
UPenn
René Vidal
Johns Hopkins
Yu-Xiang Wang
UCSB
Bihan Wen
NTU
Fanny Yang
ETH Zurich
Workshop Schedule
All times in GST (GMT+4).
Morning sessions 9 AM - 12 PM; Afternoon sessions 1:30 PM - 6 PM
- Tuesday, Jan 3 (Morning)
- Educational tutorials (Chair: Yi Ma)
- 9:00 AM - 10:00 AM
- John Wright (Columbia; remote)
- 10:00 AM - 11:00 AM
- Yuqian Zhang (Rutgers)
- 11:00 AM - 11:15 AM
- Coffee break
- 11:15 AM - 12:15 PM
- Sam Buchanan (TTIC)
- Tuesday, Jan 3 (Afternoon)
- Educational tutorials (Chair: Sam Buchanan)
- 1:30 PM - 2:30 PM
- Zhihui Zhu (Ohio State; remote)
- 2:30 PM - 3:30 PM
- Yi Ma (UC Berkeley)
- 3:30 PM - 4:00 PM
- Coffee break
- 4:00 PM - 5:00 PM
- Atlas Wang (UT Austin)
- 5:00 PM - 6:00 PM
- Saiprasad Ravishankar (Michigan State)
- Wednesday, Jan 4 (Morning)
- Invited Talks: Theory + Optimization (Chair: Qing Qu)
- 8:30 AM - 9:00 AM
- Opening (Qing Qu [UMich], Sultan Al Hajji [MBZUAI])
- 9:00 AM - 10:00 AM
- Tomaso Poggio (MIT)
- 10:00 AM - 11:00 AM
- Simon Du (UW)
- 11:00 AM - 11:30 AM
- Coffee break and poster session
- 11:30 AM - 12:30 PM
- Qi Lei (NYU)
- Wednesday, Jan 4 (Afternoon)
- Invited Talks: Image Recovery (Chair: Saiprasad Ravishankar)
- 1:30 PM - 2:30 PM
- René Vidal (JHU)
- 2:30 PM - 3:30 PM
- Mahdi Soltanolkotabi (USC)
- 3:30 PM - 4:00 PM
- Coffee break and poster session
- 4:00 PM - 5:00 PM
- Reinhard Heckel (TU Munich)
- 5:00 PM - 6:00 PM
- Bihan Wen (NTU)
- 6:00 PM - 7:30 PM
- Poster session
- Thursday, Jan 5 (Morning)
- Invited Talks: Representation Learning (Chair: Yi Ma)
- 8:30 AM - 9:00 AM
- Arrival
- 9:00 AM - 10:00 AM
- Yi Ma (UC Berkeley)
- 10:00 AM - 11:00 AM
- Weijie Su (UPenn)
- 11:00 AM - 11:15 AM
- Coffee break and poster session
- 11:15 AM - 12:15 PM
- Qing Qu (UMich)
- 12:15 PM - 12:30 PM
- Yaser Al Yousuf (Abu Dhabi Residents Office)
- Thursday, Jan 5 (Afternoon)
- Invited Talks: Implicit Bias (Chair: Yuqian Zhang)
- 1:30 PM - 2:30 PM
- Misha Belkin (UCSD)
- 2:30 PM - 3:30 PM
- Ohad Shamir (Weizmann Institute)
- 3:30 PM - 4:00 PM
- Coffee break and poster session
- 4:00 PM - 5:00 PM
- Yu-Xiang Wang (UCSB)
- 5:00 PM - 6:00 PM
- Panel, moderated by Jeremias Sulam (Eric Xing, Gitta Kutyniok, Jason Lee, Yi Ma, René Vidal)
- 6:00 PM - 7:30 PM
- Poster session
- Friday, Jan 6 (Morning)
- Invited Talks: Deep Learning + Systems (Chair: Atlas Wang)
- 8:30 AM - 9:00 AM
- Arrival
- 9:00 AM - 10:00 AM
- Gitta Kutyniok (LMU Munich)
- 10:00 AM - 11:00 AM
- Beidi Chen (Meta; remote)
- 11:00 AM - 11:30 AM
- Coffee break and poster session
- 11:30 AM - 12:30 PM
- Rina Panigrahy (Google)
- Friday, Jan 6 (Afternoon)
- Invited Talks: Data + Architectures (Chair: Sam Buchanan)
- 1:30 PM - 2:30 PM
- Daniel Soudry (Technion)
- 2:30 PM - 3:30 PM
- Ivan Dokmanić (Univ. of Basel)
- 3:30 PM - 4:00 PM
- Coffee break and poster session
- 4:00 PM - 5:00 PM
- Jason Lee (Princeton)
- 5:00 PM - 6:00 PM
- Fanny Yang (ETH Zurich)
- 6:00 PM - 7:30 PM
- Poster session
- Saturday, Jan 7
- Social Event: Tour of Le Louvre Abu Dhabi
- 9:45 AM - 12:30 PM
- Tour departs from the W Hotel
Organizers
Yi Ma
UC Berkeley
Eric P. Xing
MBZUAI
Samuel Horváth
MBZUAI
Karthik Nandakumar
MBZUAI
Martin Takáč
MBZUAI
Qing Qu
University of Michigan
Jeremias Sulam
Johns Hopkins University
Atlas Wang
UT Austin
John Wright
Columbia University
Yuqian Zhang
Rutgers University
Yuejie Chi
Carnegie Mellon University
Chong You
Google NYC
Zhihui Zhu
Ohio State University
Sam Buchanan
TTIC
Saiprasad Ravishankar
Michigan State University