Machine Learning at the Flatiron Institute

In recent years machine learning has emerged as an indispensable tool for computational science. It is also an active and growing area of study throughout the Flatiron Institute. Researchers at Flatiron are especially interested in the core areas of deep learning, probabilistic modeling, optimization, learning theory and high dimensional data analysis. They are also applying machine learning to problems in cosmological modeling, quantum many-body systems, computational neuroscience and bioinformatics. Below is a list of researchers who work in these areas; prospective visitors should feel free to contact them for more information.

Researchers in CCM

Alberto Bietti

Research Scientist, CCM
Areas of Interest: Learning theory, optimization, deep learning, kernel methods

David Blei

Visiting Scholar, CCM
Areas of Interest: Topic models, probabilistic modeling, approximate Bayesian inference

Joan Bruna

Visiting Scholar, CCM
Areas of Interest: Learning theory, deep learning, machine learning for science, high dimensional statistics, algorithms

Andreas Buja

Senior Research Scientist, CCM
Areas of Interest: Statistical methodology, model misspecification, replicability, causality, applications in the genetics of autism

Diana Cai

Flatiron Research Fellow, CCM
Areas of Interest: Probabilistic modeling, robust Bayesian inference, machine learning for science

Bob Carpenter

Senior Research Scientist, CCM
Areas of Interest: Probabilistic programming, Markov chain Monte Carlo methods, variational inference

Michael Eickenberg

Research Scientist, CCM
Areas of Interest: Machine learning for science, applied statistics and signal processing, deep learning, neuroimaging and computational cognitive neuroscience

Anna Gilbert

Visiting Scholar, CCM
Areas of Interest: Theory and algorithms for high dimensional data analysis, metric representations, non-Euclidean embeddings

Robert Gower

Research Scientist, CCM
Areas of Interest: Stochastic optimization, interpolation, adaptive methods for deep learning, convergence of algorithms and second order methods

Jiequn Han

Flatiron Research Fellow, CCM
Areas of Interest: Multiscale modeling, numerical methods for partial differential equations, machine learning for science

Stephane Mallat

Distinguished Research Scientist, CCM
Areas of Interest: Signal processing, harmonic analysis, deep learning

Charles Margossian

Flatiron Research Fellow, CCM
Areas of Interest: Probabilistic programming, Markov chain Monte Carlo methods, variational inference

Rudy Morel

Flatiron Research Fellow, CCM
Areas of Interest: Probabilistic modeling, ML for science, high-dimensional statistics, signal processing

Ruben Ohana

Flatiron Research Fellow, CCM
Areas of Interest: Deep learning, randomized algorithms, high dimensional statistics, differential privacy

Loucas Pillaud-Viven

Flatiron Research Fellow, CCM
Areas of Interest: Learning theory, optimization, deep learning

Bruno Régaldo-Saint Blancard

Flatiron Research Fellow, CCM
Areas of Interest: Machine learning for astrophysics, applied signal processing, generative modeling

Neha Wadia

Flatiron Research Fellow, CCM
Areas of Interest: Learning theory, continuous-time optimization, high dimensional statistics

Lawrence Saul

Group Leader, Machine Learning, CCM
Areas of Interest: High dimensional data analysis, latent variable models, deep learning, variational inference, kernel methods

Berfin Şimşek

Guest Researcher, CCM
Areas of Interest: Learning theory, loss landscape analysis, deep Learning

Yuling Yao

Flatiron Research Fellow, CCM
Areas of Interest: Scalable Bayesian workflows, meta-learning, causal inference

Researchers in CCN

Mitya Chklovskii

Group Leader, Neural Circuits and Algorithms, CCN
Areas of Interest: Theoretical neuroscience, connectomics, biologically inspired AI, dynamics and control

SueYeon Chung

Project Leader, Geometric Data Analysis, CCN
Areas of Interest: Theoretical neuroscience, statistical physics of learning, high dimensional geometry and statistics

Jenelle Feather

Flatiron Research Fellow, CCN
Areas of Interest: Theoretical neuroscience, analysis of high dimensional auditory and visual representations

Siavash Golkar

Associate Research Scientist, Neural Circuits and Algorithms, CCN
Areas of Interest: Biological learning, deep learning, machine learning for science

Sarah Harvey

Flatiron Research Fellow, CCN
Area of Interest: Theoretical neuroscience, statistical physics, ML methods for neural data analysis

Brett Larsen

Flatiron Research Fellow, CCN/CCM
Areas of Interest: Deep learning, optimization, loss-landscape analysis, sparsity, high-dimensional statistics

David Lipshutz

Associate Research Scientist, CCN
Areas of Interest: Theoretical neuroscience, neuro-inspired ML, stochastic analysis, dynamical systems

Amin Nejatbakhsh

Flatiron Research Fellow, CCN
Areas of Interest: Computational neuroscience, machine learning, statistics, dynamical systems, computer vision

Eero Simoncelli

Director, CCN
Areas of Interest: Analysis and representation of visual information in biological and artificial networks. Coding and inference

Tiberiu Tesileanu

Associate Research Scientist, Neural Circuits and Algorithms, CCN
Areas of Interest: Biological learning, deep learning

Alex Williams

Associate Research Scientist, Statistical Analysis of Neural Data, CCN
Areas of Interest: Unsupervised learning, uncertainty quantification in deep learning, topological data analysis, covariance estimation

Researchers in CCQ

Anna Dawid

Flatiron Research Fellow, CCQ
Areas of Interest: Machine learning for (quantum) science, interpretability, deep learning theory

Domenico Di Sante

Affiliate Research Fellow, CCQ
Areas of Interest: Theoretical neuroscience, statistical physics of learning, high dimensional geometry and statistics

Antoine Georges

Director, CCQ
Areas of Interest: Machine learning for quantum systems

Matija Medvidović

Graduate Student, CCQ
Areas of Interest: Machine learning for many-body quantum physics, sampling, optimization

Andrew Millis

Co-Director, CCQ
Areas of Interest: Theoretical condensed matter physics, high-temperature superconductivity, numerical methods for the many-electron problem

Alev Orfi

Graduate Student, CCQ
Areas of Interest: Neural quantum states, variational Monte Carlo, sampling algorithms

Anirvan Sengupta

Visiting Scholar, CCQ
Areas of Interest: Representation learning, dynamics and control, applications to quantum systems, systems neuroscience

Christopher Roth

Flatiron Research Fellow, CCQ
Areas of Interest: Neural quantum states, equivariant models, variational Monte Carlo

Jaylyn C. Umana

Graduate Student, CCQ
Areas of Interest: Symbolic regression, neural networks, optimization

Agnes Valenti

Flatiron Research Fellow, CCQ
Areas of Interest: TBD

Jiawei Zang

Graduate Student, CCQ
Areas of Interest: Machine learning for many-body quantum physics, dimensionality reduction

Researchers in CCB

Xi Chen

Research Scientist, CCB
Areas of Interest: Distribution learning, Markov chain Monte Carlo, semi-supervised learning

Adam Lamson

Flatiron Research Fellow, CCB
Areas of Interest: Interpretable neural networks, biophysical and genomics modeling, reservoir computing

Suryanarayana Maddu

Flatiron Research Fellow, CCB
Areas of Interest: Physics-informed machine learning, statistical learning theory, high dimensional statistics

Zhicheng Pan

Flatiron Research Fellow, CCB
Areas of Interest: Deep learning for genomics, graphical neural networks

Christopher Park

Research Scientist, CCB
Areas of Interest: Probabilistic modeling, deep learning and statistical genetics

Natalie Sauerwald

Flatiron Research Fellow, CCB
Areas of Interest: Machine learning for genomics and genetics, optimization, interpretable models

Rachel Sealfon

Research Scientist, CCB
Areas of Interest: Machine learning for genomics, analysis of functional genomic data

Olga Troyanskaya

Deputy Director for Genomics, CCB
Areas of interest: Genomics and bioinformatics

Mao Weiguang

Flatiron Research Fellow, CCB
Areas of Interest: Deep learning, graphical models, dimensionality reduction

Researchers in CCA

Miles Cranmer

Flatiron Research Fellow, CCA
Areas of Interest: Open-source tooling, model interpretability, learning to simulate, learned coarsening, physics-based inductive biases, graph neural networks, sparsity, symbolic regression/program synthesis, model distillation

Daniel Foreman-Mackey

Research Scientist, CCA
Areas of Interest: Probabilistic programming, Markov chain Monte Carlo, Gaussian Processes

Shirley Ho

Group Leader, Cosmology X Data Science, CCA
Areas of Interest: Machine learning for science, deep learning for simulation, neuro-symbolic models, high dimensional inference

David W. Hogg

Group Leader, Astronomical Data, CCA
Areas of Interest: Causal models, enforcing physical symmetries, adversarial attacks, models of cameras and spectrographs

Chirag Modi

Flatiron Research Fellow, Cosmology X Data Science, CCA joint with CCM
Areas of Interest: Machine learning for science, differentiable simulations, Markov chain Monte Carlo methods, approximate Bayesian inference

Francisco Villaescusa-Navarro

Research Scientist, CCA
Areas of Interest: Neuro-simulations, graph neural netwoks, likelihood-free inference, manifold learning, generative models, symmetries for deep learning.

Kaze Wong

Flatiron Research Fellow, Gravitational Wave Astronomy, CCA
Areas of Interest: Deep learning for data analysis and simulation in astrophysics

 

Events

Machine learning events at Flatiron Institute come in two flavors: one-time events like workshops, conferences or schools and a regular seminar series, ML@FI. You can find incoming events and selected archived past events below.

ML@FI is a seminar series focused on machine learning and its applications to science. It is aimed at Flatiron Institute research scientists and our collaborators. Seminars usually take place every other Tuesday at 3:00 p.m. in the CCN classroom on the fourth floor of 160 Fifth Ave or in the CCA 5th floor classroom at 162. Each meeting is followed by a reception to encourage inter-center interactions. See the website for past seminars and their recordings!

For more information, to join the seminar mailing list or to propose speakers for future seminars, please contact the organizers: Shirley Ho, Alberto Bietti, and Francois Lanusse.

The Machine Learning New York City (ML-NYC) Speaker Series is a monthly event for machine learning practitioners, researchers, and students to meet and watch talks from leading researchers in the field. Each event will feature a New York City-based speaker presenting their work. The ML-NYC Speaker Series is open to anyone interested in machine learning, and we encourage everyone to attend, whether you are a beginner or an expert in the field.

For more information or to propose speakers for future seminars, please contact the organizers: Lawrence Saul, David Blei and Joan Bruna

Advancing Research in Basic Science and MathematicsSubscribe to Flatiron Institute announcements and other foundation updates