Boulder School 2027: Machine Learning and Condensed Matter

July 5-30, 2027

Scientific Coordinators

Roger G. Melko (University of Waterloo & Perimeter Institute)
Ehsan Khatami (San Jose State University)
Juan Carrasquilla (ETH)
Leo Radzihovsky (University of Colorado, Boulder)

Director: Leo Radzihovsky (University of Colorado, Boulder)

Caption: Neural correlations in a triangular lattice structure factor.This image is adapted from the original by Schuyler Moss.

Machine learning is rapidly reshaping condensed matter and quantum many-body physics, enabling new approaches to understanding strongly correlated electrons, atomic matter, quantum devices, and more. At the same time, the learning algorithms themselves present fascinating phenomena for physicists to study, from generalization, to emergence, to the striking scaling laws observed in modern large language models. This summer school will introduce graduate students to the growing exchange of ideas between machine learning and many-body physics. The program will provide foundations in modern machine learning theory and methods, and explore applications to superconductivity, magnetism, atomic systems, and quantum simulators, including both a data-driven as well as a variational simulation perspective. Lectures from physicists and machine learning researchers will highlight recent progress and the growing exchange of ideas between these fields. The goal is to equip students with practical tools for frontier problems in condensed matter physics, while also showing how ideas from statistical mechanics, quantum many-body physics, and field theory can help illuminate the learning problem itself.

Lecturers and topics

Introduction to machine learning theory & methods (July 5-9)

Roger Melko (Waterloo): The learning problem; data, machine and loss.Foundational connections between machine learning and condensed matter physics
Yasaman Bahri (Google): Large-width neural networks, mean-field limits. Statistical mechanics, correlations, fluctuations, and criticality
Bernd Rosenow (Leipzig): Statistical mechanics and machine learning. Ensembles, random matrices, generalization, phase transitions
Ying Wai Li (LANL): Monte Carlo, sampling, optimization. Spin models, thermodynamics, phase transitions, materials simulation

Data-driven learning in classical and quantum systems (July 12-16)

Yi-Zhuang You (UCSD): Quantum data, measurements, and models. Entanglement, quantum phases, measurement-induced phenomena, quantum processors
Ehsan Khatami (San Jose): Learning and strongly correlated electrons. Hubbard models, quantum Monte Carlo, magnetism, competing phases
Timothy Hsieh (Perimeter): Markov length, CMI and phases of matter.  Mixed states, decoherence, correlation length, phase stability
Kipton Barros (LANL): Spin systems, interatomic potentials, molecules.  Frustrated magnetism, effective Hamiltonians, atomistic and materials modeling

Neural quantum states (July 19-23)

Christopher Roth (Flatiron/UBC): NQS for interacting fermions. Hubbard models, superconductivity, frustration, quantum spin liquids
Annabelle Bohrdt (Munich): Hubbard models and more. Mott physics, magnetic polarons, quantum gas microscopy
Juan Carrasquilla (Zurich): Hamiltonian-driven variational learning. Variational Monte Carlo, many-body wavefunctions, entanglement, quantum spin systems

Frontiers in physics and artificial intelligence (July 26-30)

Agnes Valenti (Flatiron): Generalization, double descent. Neural quantum states, variational Monte Carlo, frustrated quantum matter
Zohar Ringel (Hebrew/Perimeter): RG, neural scaling laws, complexity. Relevance, universality, scale dependence, power-law learning curves
Miles Stoudenmire (Flatiron): Tensor networks & neural networks. Entanglement, MPS, high-dimensional representations, tensor cross interpolation
Andrey Gromov (Meta): Grokking, emergence and scaling laws. Phase transitions, criticality, and scale dependence