Challenges and Prospects of ML for the Physical Sciences

Jun 13, 2022, 8:30 AM → Jun 17, 2022, 4:30 PM America/New_York

Ingrid Daubechies Auditorium/2-IDA (162 5th Avenue)

Our goal is to gather a diverse community of researchers at the cross-roads of ML, Statistics, Applied Mathematics and Physics to exchange views and ideas on current successes and roadblocks of data-driven tools applied to computational science. 

Monday, June 13

8:30 AM Breakfast

1 Joan Bruna

Exponential Separations in Symmetric and Anti-Symmetric Neural Networks

Speaker: Joan Bruna (NYU / CCM)

Q&A

2 Alberto Bietti

Benefits of convolutional models: a kernel perspective

Speaker: Alberto Bietti (NYU)

Q&A

10:30 AM Coffee Break

3 Yi Ma

CTRL: Closed-Loop Data Transcription via Rate Reduction

Speaker: Yi Ma (University of California, Berkeley)

Q&A

4 Soledad Villar

Dimensionless machine learning: Imposing exact units equivariance

Speaker: Soledad Villar (Johns Hopkins University)

Q&A

12:30 PM Lunch

5 CCN - Eero Simoncelli

Image Priors in the Era of Machine Learning

6 Jiequn Han

Developing reduced-order PDEs with machine learning-based closure models

Speaker: Jiequn Han (CCM, Flatiron Institute)

Q&A

3:15 PM Coffee Break

3:45 PM Working Session

Tuesday, June 14

8:30 AM Breakfast

7 Lawrence Saul

The method of sparse similarity matching for high dimensional data analysis

Speaker: Lawrence Saul (UCSD/CCM )

Q&A

8 SueYeon Chung

Efficient representation geometry in distributed neural networks

Speaker: SueYeon Chung (CCN)

Q&A

10:30 AM Coffee Break

9 Rose Yu

Approximately Equivariant Networks for Imperfectly Symmetric Dynamics

Speaker: Rose Yu (UCSD)

Q&A

10 Léon Bottou

Out-of-distribution generalization and causation

Speaker: Léon Bottou (Facebook)

Q&A

12:30 PM Lunch

2:00 PM CCB - Mike Shelley

11 Michael Mahoney

Continuous Network Models for Sequential Predictions

Speaker: Michael Mahoney (UC Berkeley )

Q&A

12 Kyle Cranmer

Speaker: Kyle Cranmer (NYU)

Q&A

4:00 PM Coffee Break

4:30 PM Working Session

Wednesday, June 15

8:30 AM Breakfast

13 Maarten de Hoop

Deep learning, active tectonics and planetary exploration

Speaker: Maarten de Hoop (Rice University )

Q&A

14 Marylou Gabrié

Enhancing Sampling with Learning

Speaker: Marylou Gabrié (Ecole Polytechnique)

Q&A

10:30 AM Coffee Break

15 Shirley Ho

Interpretable Machine Learning for Astrophysics

Speaker: Shirley Ho (CCA )

Q&A

16 Giuseppe Carleo

Variational quantum states in the age of machine learning

Speaker: Giuseppe Carleo (École Polytechnique)

Q&A

12:30 PM Lunch

2:00 PM CCA - David Hogg

17 Wenda Zhou

Spatial equivariance and deep networks: practical approaches and challenges

Speaker: Wenda Zhou (NYU/CCM )

Q&A

18 Tommaso Biancalani

Deep learning for virtual screens of antibiotics

Speaker: Tommaso Biancalani (Genentech )

Q&A

4:00 PM Coffee Break

4:30 PM Working Session

5:30 PM Dinner at BLACKBARN Restaurant

19 E 26th St, New York, NY 10010

Thursday, June 16

8:30 AM Breakfast

19 Robert Gower

Adaptive Stochastic Gradient Methods that leverage Interpolation

Speaker: Robert Gower (CCM )

Q&A

20 Eric Vanden Eijnden

Probability flow solution of the Fokker-Planck equation

Speaker: Eric Vanden Eijnden (NYU)

Q&A

10:30 AM Coffee Break

21 Leslie Greengard

Electromagnetic/acoustic design optimization

Speaker: Leslie Greengard (CCM )

Q&A

22 Yongji Wang

Physics-informed Neural Networks for fluid dynamics

Speaker: Yongji Wang (Princeton University )

Q&A

12:30 PM Lunch

2:00 PM CCQ - Domenico Di Sante

23 Miles Cranmer

One Trick to Improve Regularized Training of Neural Networks

Speaker: Miles Cranmer (Princeton University/CCA)

Q&A

24 Stéphane Mallat

Learning and Generating Multiscale Physics

Speaker: Stéphane Mallat (Collège de France/CCM )

Q&A

4:00 PM Working Session

Friday, June 17

8:30 AM Breakfast

9:00 AM Working Session

11:00 AM Lunch to-go