Workshop II: PDE and Inverse Problem Methods in Machine Learning

Part of the Long Program High Dimensional Hamilton-Jacobi PDEs
April 20 - 24, 2020

Schedule

All times in this Schedule are Pacific Time (PT)

Monday, April 20, 2020

Morning Session
8:20 - 8:30 Welcome & Opening Remarks (Dima Shlyakhtenko)

Session Chair Adam Oberman (McGill University)
8:30 - 9:20
9:30 - 9:45 Break
9:45 - 10:35
10:45 - 11:00 Break
11:00 - 11:50 Lightning Poster Presentations: Yiping Lu (Stanford); Tingwei Meng (Brown); Elisa Negrini (WPI); Mirjeta Pasha (Kent State); Lorenz Richter (FU Berlin)
12:00 - 1:00 Lunch (on your own)

Afternoon Session
1:00 - 1:50
Michael Jordan (University of California, Berkeley (UC Berkeley))

Optimization with Momentum: Dynamical, Control-Theoretic, and Symplectic Perspectives
PDF Presentation

 
2:00 - 2:15 Break
2:15 - 3:05

Tuesday, April 21, 2020

Session Chair Ivan Yegorov (NDSU)

Morning Session
8:30 - 9:20
9:30 - 9:45 Break
9:45 - 10:35
Eldad Haber (University of British Columbia)

A-optimal active learning

 
10:45 - 11:00 Break
11:00 - 11:50
12:00 - 1:00 Lunch (on your own)

Afternoon Session
1:00 - 1:50
Stefano Soatto (University of California, Los Angeles (UCLA))

Critical Periods for Regularization in Deep Neural Networks

2:00 - 2:15 Break
2:15 - 3:05

Wednesday, April 22, 2020

Session Chair Pratik Chaudhari (University of Pennsylvania)

Morning Session
8:30 - 9:20
Irène Waldspurger (Université de Paris IX (Paris-Dauphine))

Rank optimality of the Burer-Monteiro factorization
PDF Presentation

 
9:30 - 9:45 Break
9:45 - 10:35
10:45 - 11:00 Break
11:00 - 11:50
Anthony Yezzi (Georgia Institute of Technology)

Accelerated Optimization in the PDE Framework
PDF Presentation

 
12:00 - 1:00 Lunch (on your own)

Afternoon Session
1:00 - 1:50
2:00 - 2:15 Break
2:15 - 3:05
Tom Goldstein (University of Maryland)

An empirical look at generalization in neural nets

 

Thursday, April 23, 2020

Session Chair Dejan Slepcev (Carnegie Mellon University)

Morning Session
8:30 - 9:20
Wuchen Li (University of California, Los Angeles (UCLA))

Accelerated Information Gradient flow

 
9:30 - 9:45 Break
9:45 - 10:35
Christopher Finlay (McGill University)

Training neural ODEs for density estimation
PDF Presentation

 
10:45 - 11:00 Break
11:00 - 11:50
Rebecca Willett (University of Chicago)

Learning to Solve Inverse Problems in Imaging

 
12:00 - 1:00 Lunch (on your own)

Afternoon Session
1:00 - 1:50
2:00 - 2:15 Break
2:15 - 3:05
Pratik Chaudhari (University of Pennsylvania)

Learning with few labeled data
PDF Presentation

 

Friday, April 24, 2020

Session Chair Marc Sedjro (AIMS South Africa)

Morning Session
8:30 - 9:20
9:30 - 9:45 Break
9:45 - 10:35
Jeff Calder (University of Minnesota, Twin Cities)

Graph-based semi-supervised learning with very few labels

10:45 - 11:00 Break
11:00 - 11:50
12:00 Conclusion