Login

Machine Learning approaches in Lattice QCD - An interdisciplinary exchange

27 February 2023 to 3 March 2023
Institute for Advanced Study of the Technische Universität München
Europe/Berlin timezone

Contact

Contribution List

70 out of 70 displayed
  1. 102. Registration
    27/02/2023, 08:30
  2. 1. Welcome and aims of the workshop
    Nora Brambilla
    27/02/2023, 09:10
  3. 3. Machine learning is ubiquitous
    Maria-Paola Lombardo
    27/02/2023, 09:25
  4. 70. Aspects of scaling and scalability for flow-based samplers
    Daniel Hackett
    27/02/2023, 09:55
  5. 71. Learning trivializing flows
    David Albandea
    27/02/2023, 10:20
  6. 72. Fourier-Flow model generating Feynman paths
    Lingxiao Wang
    27/02/2023, 11:15
  7. 74. Stochastic normalizing flows for lattice field theory
    Elia Cellini
    27/02/2023, 11:40
  8. 75. Panel discussion
    Chair: Sinead Ryan, Members: Simone Bacchio, Daniel Hackett, Maria Paola Lombardo, Alberto Ramos
    27/02/2023, 12:00
  9. 109. Discovering mathematical structures with neural networks
    Sven Krippendorf
    27/02/2023, 14:30
  10. 111. Machine Learning at IceCube
    Rasmus Orsoe
    27/02/2023, 14:50
  11. 110. Improving Normalizing Flows to Sample from Boltzmann Distributions
    Vincent Stimper
    27/02/2023, 15:10
  12. 113. Panel discussion:
    Chair: Lukas Heinrich
    27/02/2023, 15:30
  13. 77. Signal-to-noise improvement with contour deformations
    Gurtej Kanwar
    27/02/2023, 16:30
  14. 76. Complex normalizing flows and subtractions for sign problems
    Yukari Yamauchi
    27/02/2023, 16:50
  15. 78. Applying Complex Valued Neural Networks to the Hubbard Model Sign Problem: A Survey and Case Study
    Marcel Rodekamp
    27/02/2023, 17:10
  16. 79. Panel discussion: 1. maximum improvement in <sign> 2. ML towards such a maximal improvement 3. Contour deformation for specific observables 4. Translation between observables/theories
    Chair: Will Detmold, Members: Gurtej Kanwar, Andrei Alexandru (The George Washington University), Thomas Luu, Yukari Yamauchi
    27/02/2023, 17:30

    1) Is there a way to determine the maximum improvement in <sign> or in S-to-N that is achievable through contour deformations and related
    approaches?

    2) How can ML be targeted towards such a maximal improvement?

    3) Are there features of specific observables that make contour
    deformation particularly effective or ineffective?

    4) How do contour deformations for one observable/theory...

    Go to contribution page
  17. 26. Model-Independent Learning of Quantum Phases of Matter with Quantum Convolutional Neural Networks
    Frank Pollmann
    28/02/2023, 09:50
  18. 114. Automatic differentiation for Lattice gauge theories
    Alberto Ramos
    28/02/2023, 10:20
  19. 59. Simulation of the 2D Schwinger Model via machine-learned flows in Global Correction steps
    Jacob Finkenrath
    28/02/2023, 11:15
  20. 60. Variational Autoregressive Networks for Information Theory
    Tomasz Stebel
    28/02/2023, 11:40
  21. 61. Machine-learning-assisted Monte Carlo fails at sampling computationally hard problems
    Jeanne Trinquier
    28/02/2023, 12:00
  22. 62. Panel discussion: 1. Utility of ML for lattice 2. application-specific features of gauge field generation 3. Biggest challenges 4. Applications at an interesting scale
    Chair: Phiala Shanahan, Members: Fernando Romero Lopez, Jacob Finkenrath, Jeanne Trinquier
    28/02/2023, 12:20

    • Temperature check: for each panelist, in 2-5 words, how optimistic or pessimistic do you feel about the utility of ML in accelerating lattice field generation in your context.
    • What are the most application-specific features of the LQCD gauge field generation problem i.e., in what important ways is it different from applications in other areas of physics, and how does that impact the way...

    Go to contribution page
  23. 87. Machine learning for quantum field theories with a sign problem
    Andrei Alexandru
    28/02/2023, 14:30
  24. 88. A machine learning approach to the classification of phase transitions in many flavor QCD
    Marius Neumann
    28/02/2023, 14:50
  25. 89. Teaching how to teach: defining learning samples to detect phase transitions
    Francesco Di Renzo
    28/02/2023, 15:10
  26. 90. Panel discussion: 1. Competitivity of ML for Phase identification 2. ML for Hypothesised Phases 3. Potential of ML for sign porblem
    Chair: Maria Paola Lombardo
    28/02/2023, 15:30

    Panel discussion addressing the three main questions:

    --Where do we stand with the identification of phases with ML?
    Do you feel ML could become competitive with standard techniques for the quantitative studies of known phase transitions i.e. order of the transition at large Nf, chiral limit, etc.

    --Which are your views on the need/concrete possibility of identifying hypothesised, not...

    Go to contribution page
  27. 63. Brief introduction on spectral functions and their computation
    Gert Aarts
    28/02/2023, 16:30
  28. 64. Spectral reconstruction with Gaussian processes
    Julian Urban
    28/02/2023, 16:40
  29. 65. Spectral reconstruction with neural networks
    Kai Zhou, Lingxiao Wang
    28/02/2023, 17:10
  30. 66. Learning regulators for spectral reconstruction
    Alexander Rothkopf
    28/02/2023, 17:40
  31. 67. Panel discussion
    Chair: Gert Aarts
    28/02/2023, 17:50
  32. 101. Introducing Munich Data Science Institute
    Sylvia Kortüm
    01/03/2023, 08:45
  33. 23. Learning Trivializing Gradient Flows
    Simone Bacchio
    01/03/2023, 09:00
  34. 30. An analysis of Bayesian estimates for missing higher orders in perturbative calculations
    Aleksas Mazeliauskas
    01/03/2023, 09:40
  35. 35. Generative models and EFTs
    Marina Marinkovic
    01/03/2023, 10:10
  36. 91. Finite-volume pionless EFT for multi-nucleon systems with differential programming
    Fernando Romero-Lopez
    01/03/2023, 11:10
  37. 92. Panel discussion: 1. What can EFTs do for ML4LATTICE? 2. What ML4LATTICE could do for EFTs?
    Chair: Nora Brambilla, Members: Marina Marinkovic, Phiala Shanahan, William Detmold, Aleksas Mazeliauskas
    01/03/2023, 11:40

    --what can EFTs do for ML4LATTICE?
    --what ML4LATTICE could do for EFTs?

    Go to contribution page
  38. 56. Building Transport Maps and Making Good Use of Them
    Michael Albergo
    01/03/2023, 14:30
  39. 10. Automatic differentiation for Lattice QCD
    A. Ramos
    01/03/2023, 15:00
  40. 57. Symbolic Distillation of Neural Networks
    Miles Cranmer
    01/03/2023, 15:25
  41. 58. Panel discussion: 1. Meaning of "exact" algorithms 2. in-principle vs in-practice exactness 3. applications for exactness
    Chair: Phiala Shanahan, Members: Michael Albergo, Andrei Alexandru, Miles Cranmer
    01/03/2023, 15:55

    • What does it mean to have an ML-accelerated algorithm that is “exact”?
    Discuss the distinction between exact algs, interpretable algs, and algs that allow error propagation.
    • What are the differences between in-principle and in-practice exactness? Are they important?
    • In what applications (both in LQFT and drawing parallels to other ares in physics) is it important to guarantee...

    Go to contribution page
  42. 6. How to accelerate gauge field field generation using flow-based and hybrid models
    Phiala Shanahan
    01/03/2023, 18:00
  43. 5. ML for particle physics
    Lukas Heinrich
    02/03/2023, 09:30
  44. 14. Complex Langevin real-time simulations and ML
    Alexander Rothkopf
    02/03/2023, 10:00
  45. 80. Towards fully bayesian analyses in Lattice QCD
    Julien Frison
    02/03/2023, 10:30
  46. 81. Physical Concepts from Neural Networks with Two Inputs
    Sebastian Wetzel
    02/03/2023, 11:15
  47. 82. Ab-Initio Quantum Chemistry via Graph Neural Networks
    Nicholas Gao
    02/03/2023, 11:35
  48. 83. Panel discussion on ML for physics interpretation
    Chair: Alexander Rothkopf, Members: Sebastian Wetzel, Matteo Favoni, Fernando Romero Lopez, Miles Cranmer
    02/03/2023, 12:00
    1. Alexander Rothkopf: Setting the stage – ML for physics interpretation
    2. Sebastian Wetzel: ML for identifying order parameters & effective d.o.f. in the context of phase transitions
    3. Matteo Favoni: ML for identifying defects and effective d.o.f. in the context of confinement
    4. Fernando Romero Lopez: ML for extraction of emergent d.o.f. in the context of scattering resonance
    5. Miles...
    Go to contribution page
  49. 93. Generation of gauge field configurations with equivariant neural networks
    Matteo Favoni
    02/03/2023, 14:30
  50. 95. TBA
    Daniel Hackett
    02/03/2023, 14:50
  51. 96. Panel discussion: 1. Symmetry-equivariance vs computational brute force 2. Computational challenges of gauge equivariance
    Chair: Phiala Shanahan, Members: Gurtej Kanwar, Christoph Lehner, Matteo Favoni
    02/03/2023, 15:05

    • There is ongoing debate in the ML community about the value of trying to incorporate domain knowledge into architectures vs using computational brute force. What guides your intuition for the value of building symmetry-equivariant architectures? In your experience when is symmetry-equivariance valuable and when is it not?
    • What makes gauge equivariance in particular challenging from a...

    Go to contribution page
  52. 9. ML and quantum field theories
    Gert Aarts
    03/03/2023, 09:00
  53. 41. Machine learning hadron spectral functions in Lattice QCD
    Gabor Papp
    03/03/2023, 09:30
  54. 100. R-ratio from Lattice QCD
    Jian Liang
    03/03/2023, 10:00
  55. 97. Inverse problem solving in nuclear physics with deep learning
    Kai Zhou
    03/03/2023, 10:30
  56. 98. On the extraction of hadronic spectral densities from Euclidean correlators
    Alessandro De Santis
    03/03/2023, 11:30
  57. 99. Panel discussion
    Chair: Andreas Kronfeld
    03/03/2023, 12:00
  58. 103. Machine learning for symbolic computation in high energy physics
    Abdulhakim Alnuqayqdan
    03/03/2023, 14:00
  59. 105. Alleviating the Sign Problem via Contour Deformation and Machine Learning
    Thomas Luu
    03/03/2023, 14:25
  60. 106. Gauge-equivariant neural networks as preconditioners in lattice QCD
    Christoph Lehner
    03/03/2023, 14:50
  61. 86. Deep Learning and the Standard Model: a philosophy of science perspective
    Luigi Scorzato
    03/03/2023, 15:40
  62. 108. The route towards phase transition recognition in Lattice Gauge Theories
    Andreas Athenodorou
    03/03/2023, 16:10
  63. 112. Search for Exotic Higgs Bosons using Quantum Machine Learning
    Nakul Aggarwal
    03/03/2023, 16:40
  64. 2. Summary
    Nora Brambilla
    03/03/2023, 17:00
  65. 104. Automatic differentiation for stochastic processes
    Alberto Ramos
  66. 73. Conditional Normalizing Flow model for sampling in the Critical region of Lattice Field Theory
    Ankur Singha
  67. 94. On gauge equivariant neural networks and adversarial attacks
    Daniel Schuh
  68. 8. Provably exact: AI and theoretical physics
    Phiala Shanahan
  69. 85. Reliable AI: Does the Next Generation Require Quantum Computing?
    Gitta Kutyniok
  70. 107. TBA
    Julian Mayer-Steudte