Workshop IV: Using Physical Insights for Machine Learning

November 18 - 22, 2019

Schedule

All times in this Schedule are Pacific Time (PT)

Monday, November 18, 2019

Morning Session

8:00 - 8:55 Check-In/Breakfast (Hosted by IPAM)
8:55 - 9:00 Welcome & Opening Remarks (Dima Shlyakhtenko)
9:00 - 9:50
Lenka Zdeborová (Commissariat à l'Énergie Atomique (CEA))

Understanding machine learning via exactly solvable statistical physics models
PDF Presentation

 
10:00 - 10:15 Break
10:15 - 11:05
11:15 - 11:30 Break
11:30 - 12:20
Eric Vanden-Eijnden (Courant Institute of Mathematical Sciences)

Trainability and accuracy of artificial neural networks
PDF Presentation

 
12:30 - 2:30 Lunch (on your own)

Afternoon Session

2:30 - 3:20
Risi Kondor (University of Chicago & Flatiron Institute)

Covariant neural network architectures for learning physics
PDF Presentation

 
3:30 - 3:45 Break
3:45 - 4:35
Michele Ceriotti (École Polytechnique Fédérale de Lausanne (EPFL))

Machine learning for atomic and molecular simulations
PDF Presentation

 
4:45 - 5:15 Lightning Poster Presentations
5:15 - 6:30 Reception (Hosted by IPAM) & Poster Session

Tuesday, November 19, 2019

Morning Session

8:00 - 9:00 Breakfast (hosted by IPAM)
9:00 - 9:50
Yann LeCun (Facebook)

Energy-Based Self-Supervised Learning
PDF Presentation

 
10:00 - 10:15 Break
10:15 - 11:05
11:15 - 11:30 Break
11:30 - 12:20
12:30 - 2:30 Lunch (on your own)

Afternoon Session

2:30 - 3:20
3:30 - 4:00 Break
4:00 - 4:50
 

Wednesday, November 20, 2019

Morning Session

8:00 - 9:00 Breakfast (hosted by IPAM)
9:00 - 9:50
Riccardo Zecchina (Bocconi University)

Evidence of local entropy optimization in machine learning, physics and neuroscience

 
10:00 - 10:15 Break
10:15 - 11:05
Daniel Roberts (Diffeo)

Deep learning as a toy model of the 1/N-expansion and renormalization

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

Afternoon Session

2:30 - 3:20
Maria Schuld (University of KwaZulu-Natal)

Innovating machine learning with near-term quantum computing
PDF Presentation

 
3:30 - 4:00 Break
4:00 - 4:50

Thursday, November 21, 2019

Morning Session

8:00 - 9:00 Breakfast (hosted by IPAM)
9:00 - 9:50
Andrea Montanari (Stanford University)

Thermodynamic limits for neural networks
PDF Presentation

10:00 - 10:15 Break
10:15 - 11:05
11:15 - 11:30 Break
11:30 - 12:20
12:30 - 2:30 Lunch (on your own)

Afternoon Session

2:30 - 3:30
Chris Sutton (Fritz-Haber-Institut der Max-Planck-Gesellschaft)

Subgroup Discovery for Assessing the Domain of Applicability of Machine Learning Models

 
3:30 - 4:00 Break
4:00 - 4:50
Matthias Rupp (Citrine Informatics & Fritz-Haber-Institut der Max-Planck-Gesellschaft)

How to assess scientific machine learning models? Prediction errors and predictive uncertainty quantification

 

Friday, November 22, 2019

Morning Session

8:00 - 9:00 Breakfast (hosted by IPAM)
9:00 - 9:50
10:00 - 10:15 Break
10:15 - 11:05
11:15 - 11:30 Break
11:30 - 12:20