Machine Learning Quantum Matter Data

  • Organized by
  • Portrait photo of Andrew MillisAndrew Millis, Ph.D.CCQ Co-Director, Flatiron Institute
  • Eun-Ah Kim, Ph.D.Cornell University
Date & Time


This workshop will bring together a select group of experimentalists and theorists to address the new challenges raised by the prospect of using machine learning methods to analyze the new, complex, large datasets emerging in many classes of experiments. The workshop will feature a mix of experimental and theoretical talks, along with plenty of time for discussion. Our aim is to reach a consensus on the current status, near-term possibilities, and conceptual and practical challenges of this new area of science.

  • Thursday, January 23

    8:00 - 9:00 AM Breakfast
    9:00 - 9:15 AMEun-ah Kim and Andy Millis Welcome and Overview
    9:15- 12:00 PMScanning and Tunneling Spectroscopy
    9:15 - 10:00 AM (30+15)Jenny Hoffman (Harvard University) Local correlations in disordered materials with neural networks
    10:00 - 10:45 AM (30+15)Abhay Pasupathy (Columbia University)Blind deconvolution approach to pattern recognition in STM images
    10:45 - 11:15 PM (30)Break
    11:15 - 12:00 AM (30+15)Erica Carlson (Purdue University)Fractal views on quantum materials: learning physics from surface probe imagesSlides
    12:00 - 2:00 PMLunch and Discussion
    2:00 - 4:15 PM Theory
    2:00 - 2:45 PM (30+15)Roger Melko (Perimeter Institute/Waterloo) Reconstructing quantum states with generative modelsSlides
    2:45 - 3:30 PM (30+15)Titus Neupert (University of Zurich)Many problems and some solutions for machine learning quantum matter
    3:30 - 4:15 PM (30+15)Andrew Wilson (New York University)Bayesian Deep Learning Applied to Scientific Data
    4:15 - 4:30 PM (15)Break
    4:30 - 6:00 PM Quantum Gas Microscopy
    4:30 - 5:15 PM (30+15)Giacomo Torlai (CCQ) Generative modeling of quantum simulatorsSlides
    5:15 - 6:00 PM (30+15)Eugene Demler (Harvard University)Solving real world quantum problems with simulators and machine learning

    Friday, January 24

    8:00 - 9:00 AMBreakfast
    9:00 - 12:00 PMScattering and TEM
    9:00 - 9:45 AM (30+15)Ray Osborn (Argonne National Laboratories)Challenges in Studying Correlated Disorder
    9:45 - 10:30 AM (30+15)Simon Billinge (Columbia University) Machine learning materials science from experimental and theoretical data Slides
    10:30 - 11:00 AM (30)Break
    11:00 - 11:45 AM (30+15)David Mueller (Cornell University) Phase Retrieval for Petavoxel Electron imaging as a big and deep data problem Slides
    11:45 - 12:30 PM (30+15)Sergei Kalinin (Oak Ridge National Laboratories) Causal learning from structural electron and scanning probe microscopy data
    12:30 - 2:00 PMLunch and Informal Discussion
    2:00 - 2:45 PM (30+15)Markus Greiner (Harvard University)Quantum simulation of the doped Hubbard model and machine learning
    2:00 - 4:00 PM Eun-Ah Kim (Cornell University)Summary and Discussion
  • Sayan BasakPurdue University
    Simon BillingeColumbia University
    Michael CaoCornell University
    Giuseppe CarleoCCQ
    Erica CarlsonPurdue University
    Iris CongHarvard University
    Eugene DemlerHarvard University
    Antoine GeorgesCCQ
    Paul GinspargCornell University
    Markus GreinerHarvard University
    Kaylie HausknechtHarvard University
    Jenny HoffmanHarvard University
    Sergei KalininOak Ridge National Laboratory
    Eun-Ah KimCornell University
    Guangqi LiColumbia University
    Mike MattyCornell University
    Roger MelkoUniversity of Waterloo, Perimeter Institute
    Andy MillisCCQ
    Lukas MuechlerCCQ
    David MullerCornell University
    Titus NeupertUniversity of Zurich
    Ray OsbornArgonne National Laboratories
    Miles StoudenmireCCQ
    Giacomo TorlaiCCQ
    Andrew WilsonNYU
Advancing Research in Basic Science and MathematicsSubscribe to Flatiron Institute announcements and other foundation updates