Flatiron Institute / NYU-CDS

April 29-May 1, 2019

Machine-learning methods have had great success in learning complex patterns that enable them to make predictions about unobserved data. In addition to using ML models for prediction, the ability to interpret what a model has learned is receiving an increasing amount of attention. In this targeted workshop jointly organized by NYU-CDS and Flatiron Institute in the week of April 29th, 2019, we like to bring together computer scientists, mathematicians and physicists who are interested in:

1. applying ML to various outstanding physical problems, in particular in inverse problems and approximating physical processes;
2. understanding what the learned model really represents; and
3. connecting tools and insights from physics to the study of machine learning models and in particular neural nets.

In particular, the main topics will revolve around ML, deep nets and approximation of operators and probability distributions (in physics and mathematics). These operators may result from N-body problems, from the resolution of inverse problems (inverse operators), from the resolution of PDE, the calculation of energies, forces in quantum or astrophysics.

REGISTRATIONS is closed.

Confirmed Speakers include:

• Joan Bruna
• Giuseppe Carleo
• Gabor Csyani
• Shirley Ho
• Stephane Mallat
• Max Welling
• Bin Yu
• Lenka Zdeborova

Scientific Organizing Committee:

Shirley Ho (Flatiron Institute)

Julia Kempe (New York University Center for Data Science)

Stephane Mallat (Flatiron Institute, ENS, College De France)

For logistic questions related to the workshop, contact Melanie at <mshiree@flatironinstitute.org>

For more scientifically related workshop questions, contact us