Workshop II: Theory and Practice of Deep Learning

Part of the Long Program Mathematics of Intelligences
October 14 - 18, 2024

Schedule

All times in this Schedule are Pacific Time (PT)

Monday, October 14, 2024

Morning Session
8:00 - 8:55 Check-In/Breakfast (Hosted by IPAM)
8:55 - 9:00 Welcome and Opening Remarks
9:00 SESSION CHAIR: Jacob Foster
9:00 - 9:50
Boris Hanin (Princeton University)

Neural Network Scaling Limits

10:00 - 10:15 Break
10:15 - 11:05
11:15 - 11:30 Break
11:30 - 12:20
Nikos Tsilivis (New York University)

The Price of Implicit Bias in Robust ML

12:30 - 2:30 Lunch (on your own)

Afternoon Session
2:30 SESSION CHAIR: Jacob Foster
2:30 - 3:20
3:30 - 3:45 Break
3:45 - 4:15 Lightning Poster Session
4:15 - 6:30 Poster Session & Reception (Hosted by IPAM)

Tuesday, October 15, 2024

Morning Session
8:00 - 9:00 Check-In/Breakfast (Hosted by IPAM)
9:00 SESSION CHAIR: Boris Hanin
9:00 - 9:50
10:00 - 10:15 Break
10:15 - 11:05
Gintare Karolina Dziugaite (Google DeepMind)

The dynamics of memorization and generalization in deep learning

11:15 - 11:30 Break
11:30 - 12:20
Vidya Muthukumar (Georgia Institute of Technology)

Comparison and transfer between tasks in overparameterized learning

12:30 - 2:30 Lunch (on your own)

Afternoon Session
2:30 SESSION CHAIR: Boris Hanin
2:30 - 3:20
Sam Smith (Google DeepMind)

"How to train an LLM"

3:30 - 4:00 Break
4:00 - 4:50
Patrick Shafto (Rutgers University)

Common Ground in Cooperative Communication


Wednesday, October 16, 2024

Morning Session
8:00 - 9:00 Check-In/Breakfast (Hosted by IPAM)
9:00 SESSION CHAIR: Patrick Shafto
9:00 - 9:50
10:00 - 10:15 Break
10:15 - 11:05
11:15 - 11:30 Break
11:30 - 12:20
12:30 Group Photo
12:30 - 2:30 Lunch (on your own)

Afternoon Session
2:30 SESSION CHAIR: Patrick Shafto
2:30 - 3:20
3:30 - 4:00 Break
4:00 - 4:50 Discussion

Thursday, October 17, 2024

Morning Session
8:00 - 9:00 Check-In/Breakfast (Hosted by IPAM)
9:00 SESSION CHAIR: Misha Belkin
9:00 - 9:50
10:00 - 10:15 Break
10:15 - 11:05
Dmitry Krotov (Massachusetts Institute of Technology)

Generative AI models through the lens of Dense Associative Memory

11:15 - 11:30 Break
11:30 - 12:20
12:30 - 2:30 Lunch (on your own)

Afternoon Session
2:30 SESSION CHAIR: Misha Belkin
2:30 - 3:20
3:30 - 4:00 Break
4:00 - 4:50
Mayank Mehta (University of California, Los Angeles (UCLA))

Dynamics of brain's deep network


Friday, October 18, 2024

Morning Session
8:00 - 9:00 Check-In/Breakfast (Hosted by IPAM)
9:00 SESSION CHAIR: Monty Abbas
9:00 - 9:50
Adityanarayanan Radhakrishnan (Broad Institute)

How do neural networks learn features from data?

10:00 - 10:15 Break
10:15 - 11:05
11:15 - 11:30 Break
11:30 - 12:20
Misha Belkin (University of California, San Diego (UCSD))

Emergence and grokking in "simple" architectures

12:30 - 2:30 Lunch (on your own)