Joan Bruna

• Joan Bruna (NYU / CCM)

Exponential Separations in Symmetric and Anti-Symmetric Neural Networks

Alberto Bietti

• Alberto Bietti (NYU)

Benefits of convolutional models: a kernel perspective

Yi Ma

• Yi Ma (University of California, Berkeley)

CTRL: Closed-Loop Data Transcription via Rate Reduction

Soledad Villar

• Soledad Villar (Johns Hopkins University)

Dimensionless machine learning: Imposing exact units equivariance

CCN - Eero Simoncelli Image Priors in the Era of Machine Learning

Jiequn Han

• Jiequn Han (CCM, Flatiron Institute)

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

Lawrence Saul

• Lawrence Saul (UCSD/CCM )

The method of sparse similarity matching for high dimensional data analysis

SueYeon Chung

• SueYeon Chung (CCN)

Efficient representation geometry in distributed neural networks

Rose Yu

• Rose Yu (UCSD)

Approximately Equivariant Networks for Imperfectly Symmetric Dynamics

Léon Bottou

• Léon Bottou (Facebook)

Out-of-distribution generalization and causation

Michael Mahoney

• Michael Mahoney (UC Berkeley )

Continuous Network Models for Sequential Predictions

Kyle Cranmer

• Kyle Cranmer (NYU)

Maarten de Hoop

• Maarten de Hoop (Rice University )

Deep learning, active tectonics and planetary exploration

Marylou Gabrié

• Marylou Gabrié (Ecole Polytechnique)

Enhancing Sampling with Learning

Shirley Ho

• Shirley Ho (CCA )

Interpretable Machine Learning for Astrophysics

Giuseppe Carleo

• Giuseppe Carleo (École Polytechnique)

Variational quantum states in the age of machine learning

Wenda Zhou

• Wenda Zhou (NYU/CCM )

Spatial equivariance and deep networks: practical approaches and challenges

Tommaso Biancalani

• Tommaso Biancalani (Genentech )

Deep learning for virtual screens of antibiotics

Robert Gower

• Robert Gower (CCM )

Adaptive Stochastic Gradient Methods that leverage Interpolation

Eric Vanden Eijnden

• Eric Vanden Eijnden (NYU)

Probability flow solution of the Fokker-Planck equation

Leslie Greengard

• Leslie Greengard (CCM )

Electromagnetic/acoustic design optimization

Yongji Wang

• Yongji Wang (Princeton University )

Physics-informed Neural Networks for fluid dynamics

Miles Cranmer

• Miles Cranmer (Princeton University/CCA)

One Trick to Improve Regularized Training of Neural Networks

Stéphane Mallat

• Stéphane Mallat (Collège de France/CCM )

Learning and Generating Multiscale Physics