Machine learning approaches in Lattice QCD - an interdisciplinary exchange

Europe/Zurich
HCI G7 (ETH Zürich)

HCI G7

ETH Zürich

Stefano-Franscini-Platz 5 8093 Zürich
Marina Krstic Marinkovic (ETH Zurich), Roman Gruber
Description

This is the second edition of the workshop previously held at TU Munich in 2023 (https://indico.ph.tum.de/event/7116/).

 

This edition of the workshop will take place at ETH Zurich from 10th to 13th June 2025 and will serve as an interdisciplinary exchange to accelerate the development of machine learning techniques in Lattice Gauge Theories. The workshop will bring together experts in Machine Learning, Lattice QCD, and related fields. The last day of the event will feature international and local experts focusing on the development of efficient simulation software for various GPU architectures, with contributions from both the Lattice QCD and HPC communities.

 

Participants of this workshop are encouraged to also attend the PASC25 conference, which will be held the week following this workshop, from 16th to 18th June 2025, at FHNW in Brugg-Windisch. The PASC25 venue is conveniently accessible by public transportation in less than an hour from Zurich main station.

 

Confirmed speakers include:

  • Alexander Rothkopf (Korea University) 
  • Alberto Ramos (U. Valencia)
  • Andreas Kronfeld (Fermilab)
  • Fernando Romero-Lopez (University of Bern)
  • Gert Aarts (Swansea University) 
  • Steven Gottlieb (Indiana University)
  • Tom Luu (FZ Jülich/University of Bonn)
  • Will Detmold (MIT)
  • Jessica Howard (UCSB)
  • Evan Weinberg (NVIDIA)
  • Urs Wenger (U. Bern)

 

Local organizers (ETHZ):

  • Javad Komijani
  • Roman Gruber
  • Marina Marinkovic
  • Letizia Parato
  • Tim Harris

 

Advisory Committee:

  • Gert Aarts (Swansea University and ECT*) 
  • Nora Brambilla (TUM)
  • William Detmold (MIT)
  • Lukas Heinrich (TUM)
  • Andreas Kronfeld (Fermilab)
  • Marina Marinkovic (ETH Zurich)
  • Maria Paola Lombardo (Firenze INFN)
  • Mike Peardon (Trinity College Dublin)
  • Alexander Rothkopf (Korea University)
  • Sinéad Ryan (Trinity College Dublin) 
  • Phiala Shanahan (MIT)

 

Registration
Registration DL for participation is 25 May 2025.
Participants
    • 9:00 AM 9:50 AM
      Registration 50m HCI G7

      HCI G7

      ETH Zürich

      Stefano-Franscini-Platz 5 8093 Zürich
    • 9:50 AM 10:00 AM
      Welcome 10m HCI G7

      HCI G7

      ETH Zürich

      Stefano-Franscini-Platz 5 8093 Zürich
      Speaker: Marina Krstic Marinkovic (ETH Zurich)
    • 10:00 AM 10:50 AM
      Optimal transport for anomaly detection at LHC 50m HCI G7

      HCI G7

      ETH Zürich

      Stefano-Franscini-Platz 5 8093 Zürich
      Speaker: Jessica N. Howard (Kavli Institute for Theoretical Physics)
    • 10:50 AM 11:30 AM
      Coffee break 40m HCI G7

      HCI G7

      ETH Zürich

      Stefano-Franscini-Platz 5 8093 Zürich
    • 11:30 AM 12:20 PM
      Machine learning RG-improved SU(3) gauge actions 50m HCI G7

      HCI G7

      ETH Zürich

      Stefano-Franscini-Platz 5 8093 Zürich

      I describe how RG-improved SU(3) gauge actions can be parametrized through machine learning gauge covariant convolutional neural networks. I discuss how the approach benefits from the straightforward accessibility of gauge field derivatives and the capability to generate targeted learning.

      Speaker: Urs Wenger (University of Bern)
    • 12:20 PM 2:00 PM
      Lunch 1h 40m

      https://ethz.ch/de/campus/erleben/gastronomie-und-einkaufen/gastronomie/restaurants-und-cafeterias/hoenggerberg.html

    • 2:00 PM 2:35 PM
      Stochastic differentiation of Monte Carlo simulations for parameter inference in quarkonium suppression 35m HCI G7

      HCI G7

      ETH Zürich

      Stefano-Franscini-Platz 5 8093 Zürich

      In many scientific domains, phenomena are being described by demanding Monte Carlo simulations. A common problem setting is that these simulations depend on input parameters, whose values are a priori not clear. To determine the input parameters one usually falls back to fitting the output of the simulator to some target. This can become particularly challenging, when the simulator is expensive to evaluate and the number of input parameters increases. In this talk I will discuss the approach of differentiating the simulator, which enables parameter inference by gradient descent. For Monte Carlo simulations involving discrete probabilities it is possible to build on the REINFORCE gradient estimator to differentiate the full stochastic simulation. I demonstrate this method for the simulation of quarkonium suppression. Quarkonium suppression refers to the phenomenon of bound states dissociating in the quark gluon plasma and can be measured by the nuclear modification factor R_{AA}. The underlying simulator that predicts this suppression solves a Lindblad equation by sampling stochastic trajectories. I showcase how to obtain a low variance gradient estimator and fit the quarkonium transport coefficients to nuclear modification factor data.

      Speaker: Tom Magorsch
    • 2:35 PM 3:10 PM
      Optimizing static quark states with Neural Network parametrized general Wilson loops 35m HCI G7

      HCI G7

      ETH Zürich

      Stefano-Franscini-Platz 5 8093 Zürich
      Speaker: Julian Mayer-Steudte
    • 3:10 PM 3:40 PM
      Coffee break 30m HCI G7

      HCI G7

      ETH Zürich

      Stefano-Franscini-Platz 5 8093 Zürich
    • 3:40 PM 4:30 PM
      Protecting continuum symmetries on the lattice - exact prior information for reinforcement learning 50m HCI G7

      HCI G7

      ETH Zürich

      Stefano-Franscini-Platz 5 8093 Zürich
      Speaker: Prof. Alexander Rothkopf (Korea University)
    • 4:30 PM 5:15 PM
      Discussion 45m HCI G7

      HCI G7

      ETH Zürich

      Stefano-Franscini-Platz 5 8093 Zürich
      Speaker: Nora brambilla
    • 5:30 PM 7:00 PM
      Welcome Apéro 1h 30m Bellavista

      Bellavista

      Honggerbergring 47, 8093 Zurich, Zürich, CH 8093

      https://maps.app.goo.gl/gFzm4v1YQ4S4Waj9A

    • 10:00 AM 10:35 AM
      Monte Carlo estimates of flow fields for sampling and noise problems 35m HCI G7

      HCI G7

      ETH Zürich

      Stefano-Franscini-Platz 5 8093 Zürich
      Speaker: Gurtej Kanwar (University of Edinburgh)
    • 10:35 AM 11:20 AM
      Coffee break 45m HCI G7

      HCI G7

      ETH Zürich

      Stefano-Franscini-Platz 5 8093 Zürich
    • 11:20 AM 12:10 PM
      Applications of flow models to the generation of correlated lattice QCD ensembles 50m HCI G7

      HCI G7

      ETH Zürich

      Stefano-Franscini-Platz 5 8093 Zürich

      Machine-learned normalizing flows can be used in the context of lattice quantum field theory to generate statistically correlated ensembles of lattice gauge fields at different action parameters. In this talk, we show examples on how these correlations can be exploited for variance reduction in the computation of observables. Different proof-of-concept applications are presented: continuum limits of gauge theories, the mass dependence of QCD observables, hadronic matrix elements based on the Feynman-Hellmann approach, and the computation of glueball correlators. In all cases, statistical uncertainties are significantly reduced when machine-learned flows are incorporated as compared with the same calculations performed with uncorrelated ensembles or direct reweighting.

      Speaker: Fernando Romero López
    • 12:10 PM 1:50 PM
      Lunch 1h 40m
    • 1:50 PM 2:25 PM
      Applications of Stochastic Normalizing Flows to gauge theories and defects 35m HCI G7

      HCI G7

      ETH Zürich

      Stefano-Franscini-Platz 5 8093 Zürich

      In recent years, flow-based samplers have emerged as a promising alternative to standard sampling methods in lattice field theory. In this talk, I will introduce a class of flow-based samplers known as Stochastic Normalizing Flows (SNFs), which are hybrid algorithms combining neural networks and non-equilibrium Monte Carlo methods. I will then demonstrate that SNFs exhibit excellent scaling with volume in lattice SU(3) gauge theory. Afterward, I will discuss theories with defects and present a general strategy for applying flow-based samplers to such systems. In particular, I will showcase an application of our approach to scalar field theory for calculating entanglement entropy, as well as an application to SU(3) gauge theory aimed at addressing topological freezing.

      Speaker: Elia Cellini (University of Turin / INFN Turin)
    • 2:25 PM 3:00 PM
      Application of generative models on SU(3) gauge theories in 4 dimension 35m HCI G7

      HCI G7

      ETH Zürich

      Stefano-Franscini-Platz 5 8093 Zürich
      Speaker: Javad Komijani (ETH Zurich)
    • 3:00 PM 3:40 PM
      Coffee break 40m HCI G7

      HCI G7

      ETH Zürich

      Stefano-Franscini-Platz 5 8093 Zürich
    • 3:40 PM 4:40 PM
      Discussion 1h HCI G7

      HCI G7

      ETH Zürich

      Stefano-Franscini-Platz 5 8093 Zürich
      Speakers: Marina Krstic Marinkovic (ETH Zurich), Prof. Sinead Ryan (Trinity College Dublin)
    • 4:40 PM 5:15 PM
      Score-Based Diffusion Models for Lattice Gauge Theory 35m HCI G7

      HCI G7

      ETH Zürich

      Stefano-Franscini-Platz 5 8093 Zürich
      Speaker: Octavio Vega
    • 7:00 PM 10:00 PM
      Workshop Dinner 3h Restaurant Linde Oberstrass

      Restaurant Linde Oberstrass

      Universitätstrasse 91, 8006 Zürich
    • 10:00 AM 10:50 AM
      Progress in learning contour deformations for observables 50m HCI G7

      HCI G7

      ETH Zürich

      Stefano-Franscini-Platz 5 8093 Zürich
      Speaker: William Detmold
    • 10:50 AM 11:30 AM
      Coffee break 40m HCI G7

      HCI G7

      ETH Zürich

      Stefano-Franscini-Platz 5 8093 Zürich
    • 11:30 AM 12:20 PM
      Diffusion models for lattice field theory 50m HCI G7

      HCI G7

      ETH Zürich

      Stefano-Franscini-Platz 5 8093 Zürich
      Speaker: Prof. Gert Aarts (Swansea University)
    • 12:20 PM 1:50 PM
      Lunch 1h 30m
    • 1:50 PM 2:40 PM
      Machine Learning Low-D Systems 50m HCI G7

      HCI G7

      ETH Zürich

      Stefano-Franscini-Platz 5 8093 Zürich

      I discuss how machine learning is used in stochastic simulations of low-D strongly correlated systems. In particular, I show how machine learning is used to alleviate the numerical sign problem in systems that are doped and/or non-bipartite. I further discuss how flow-based generative models can be used to address ergodicity issues in low-D simulations. Finally, I argue that low-D systems offer a great testbed for testing novel algorithms that could potentially be used in lattice gauge theory simulations.

      Speaker: Prof. Thomas Luu (Forshungszentrum Jülich)
    • 2:40 PM 3:15 PM
      Simulations of machine-learned RG-improved SU(3) gauge action 35m HCI G7

      HCI G7

      ETH Zürich

      Stefano-Franscini-Platz 5 8093 Zürich
      Speaker: Kieran Holland
    • 3:15 PM 3:45 PM
      Coffee break 30m HCI G7

      HCI G7

      ETH Zürich

      Stefano-Franscini-Platz 5 8093 Zürich
    • 3:45 PM 4:20 PM
      Efficient Multilevel Sampling of Lattice Field Theory Near Criticality 35m HCI G7

      HCI G7

      ETH Zürich

      Stefano-Franscini-Platz 5 8093 Zürich

      We present a hierarchical generative framework for efficient sampling of scalar field configurations near criticality. The method leverages a multiscale structure where coarse and intermediate fields are sampled via conditionally constructed Gaussian Mixture Models (GMMs). Normalizing Flows (NFs) refine these samples through invertible transformations that match the target distribution. This approach enables high Effective Sample Size (ESS) and mitigates critical slowing down. Our results demonstrate improved scalability and accuracy over traditional and superresolution-based methods.

      Speaker: Ankur Singha
    • 4:20 PM 5:10 PM
      Stochastic automatic differentiation for Lattice QCD 50m HCI G7

      HCI G7

      ETH Zürich

      Stefano-Franscini-Platz 5 8093 Zürich
      Speaker: Alberto Ramos Martinez (Univ. of Valencia and CSIC (ES))
    • 5:10 PM 5:55 PM
      Discussion 45m HCI G7

      HCI G7

      ETH Zürich

      Stefano-Franscini-Platz 5 8093 Zürich
      Speaker: Andreas Kronfeld (Fermi National Accelerator Lab. (US))
    • 10:00 AM 10:35 AM
      Random Matrix Theory for a nano-GPT 35m HCI G7

      HCI G7

      ETH Zürich

      Stefano-Franscini-Platz 5 8093 Zürich
      Speaker: Ouraman Hajizadeh (Independent Researcher)
    • 10:35 AM 11:25 AM
      Optimized Multi-Grid Solvers: Power, Precision, and (Matrix) Products 50m HCI G7

      HCI G7

      ETH Zürich

      Stefano-Franscini-Platz 5 8093 Zürich
      Speaker: Evan Weinberg (NVIDIA Corporation)
    • 11:25 AM 11:55 AM
      Coffee break 30m HCI G7

      HCI G7

      ETH Zürich

      Stefano-Franscini-Platz 5 8093 Zürich
    • 11:55 AM 12:45 PM
      Recent Performance Using MILC and QUDA on Various GPU Systems 50m HCI G7

      HCI G7

      ETH Zürich

      Stefano-Franscini-Platz 5 8093 Zürich

      I plan to show performance data for the MILC code calling QUDA
      for configuration generation. There will be a combination of
      benchmark runs and production runs on various systems. I will
      also show some recent results for deflation, multigrid, and
      gauge flow performed by Leon Hostetler with the assitance of Evan
      Weinberg. If there is time I will discuss some work to prepare
      for a new ensemble with a lattice spacing of about 0.03 fm and
      physically light quarks.

      Speaker: Steven Gottlieb
    • 12:45 PM 1:00 PM
      Closing 15m HCI G7

      HCI G7

      ETH Zürich

      Stefano-Franscini-Platz 5 8093 Zürich
      Speaker: Marina Krstic Marinkovic (ETH Zurich)
    • 1:00 PM 2:00 PM
      Lunch 1h