Machine Learning approaches in Lattice QCD - An interdisciplinary exchange

Material Package

Added Since

Include only attachments uploaded after this date

Include*

Everything

Specific sessions

Specific contributions

Specific days

Sessions*

Generative flow methods

Poster session (With food and drinks)

ML for particle physics

Symmetry equivariant neural networks/informed neural networks

Spectral Reconstruction

Inverse Problem

ML for physical interpretation of lattice results

ML as component of exact algorithms

ML for phase transitions and sign problem mitigation

EFT, Lattice and ML

Gauge field generation

Include materials from selected sessions

Contributions*

A machine learning approach to the classification of phase transitions in many flavor QCD (in session "ML for phase transitions and sign problem mitigation")

Ab-Initio Quantum Chemistry via Graph Neural Networks (in session "ML for physical interpretation of lattice results")

Alleviating the Sign Problem via Contour Deformation and Machine Learning (in session "EFT, Lattice and ML")

An analysis of Bayesian estimates for missing higher orders in perturbative calculations (in session "EFT, Lattice and ML")

Applying Complex Valued Neural Networks to the Hubbard Model Sign Problem: A Survey and Case Study (in session "ML for phase transitions and sign problem mitigation")

Aspects of scaling and scalability for flow-based samplers (in session "Generative flow methods")

Automatic differentiation for Lattice gauge theories

Automatic differentiation for Lattice QCD (in session "ML as component of exact algorithms")

Brief introduction on spectral functions and their computation (in session "Spectral Reconstruction")

Building Transport Maps and Making Good Use of Them (in session "ML as component of exact algorithms")

Complex Langevin real-time simulations and ML

Complex normalizing flows and subtractions for sign problems (in session "ML for phase transitions and sign problem mitigation")

Deep Learning and the Standard Model: a philosophy of science perspective (in session "EFT, Lattice and ML")

Discovering mathematical structures with neural networks (in session "ML for particle physics")

Finite-volume pionless EFT for multi-nucleon systems with differential programming (in session "EFT, Lattice and ML")

Fourier-Flow model generating Feynman paths (in session "Generative flow methods")

Gauge-equivariant neural networks as preconditioners in lattice QCD (in session "EFT, Lattice and ML")

Generation of gauge field configurations with equivariant neural networks (in session "Symmetry equivariant neural networks/informed neural networks")

Generative models and EFTs (in session "EFT, Lattice and ML")

How to accelerate gauge field field generation using flow-based and hybrid models

Improving Normalizing Flows to Sample from Boltzmann Distributions (in session "ML for particle physics")

Introducing Munich Data Science Institute

Inverse problem solving in nuclear physics with deep learning (in session "Inverse Problem")

Learning regulators for spectral reconstruction (in session "Spectral Reconstruction")

Learning trivializing flows (in session "Generative flow methods")

Learning Trivializing Gradient Flows (in session "EFT, Lattice and ML")

Machine Learning at IceCube (in session "ML for particle physics")

Machine learning for quantum field theories with a sign problem (in session "ML for phase transitions and sign problem mitigation")

Machine learning for symbolic computation in high energy physics (in session "EFT, Lattice and ML")

Machine learning hadron spectral functions in Lattice QCD (in session "Inverse Problem")

Machine learning is ubiquitous

Machine-learning-assisted Monte Carlo fails at sampling computationally hard problems (in session "Gauge field generation")

ML and quantum field theories

ML for particle physics

Model-Independent Learning of Quantum Phases of Matter with Quantum Convolutional Neural Networks

On the extraction of hadronic spectral densities from Euclidean correlators (in session "Inverse Problem")

Panel discussion (in session "Inverse Problem")

Panel discussion (in session "Generative flow methods")

Panel discussion (in session "Spectral Reconstruction")

Panel discussion on ML for physics interpretation (in session "ML for physical interpretation of lattice results")

Panel discussion: (in session "ML for particle physics")

Panel discussion: 1. Competitivity of ML for Phase identification 2. ML for Hypothesised Phases 3. Potential of ML for sign porblem (in session "ML for phase transitions and sign problem mitigation")

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 (in session "ML for phase transitions and sign problem mitigation")

Panel discussion: 1. Meaning of "exact" algorithms 2. in-principle vs in-practice exactness 3. applications for exactness (in session "ML as component of exact algorithms")

Panel discussion: 1. Symmetry-equivariance vs computational brute force 2. Computational challenges of gauge equivariance (in session "Symmetry equivariant neural networks/informed neural networks")

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 (in session "Gauge field generation")

Panel discussion: 1. What can EFTs do for ML4LATTICE? 2. What ML4LATTICE could do for EFTs? (in session "EFT, Lattice and ML")

Physical Concepts from Neural Networks with Two Inputs (in session "ML for physical interpretation of lattice results")

R-ratio from Lattice QCD (in session "Inverse Problem")

Registration

Search for Exotic Higgs Bosons using Quantum Machine Learning (in session "EFT, Lattice and ML")

Signal-to-noise improvement with contour deformations (in session "ML for phase transitions and sign problem mitigation")

Simulation of the 2D Schwinger Model via machine-learned flows in Global Correction steps (in session "Gauge field generation")

Spectral reconstruction with Gaussian processes (in session "Spectral Reconstruction")

Spectral reconstruction with neural networks (in session "Spectral Reconstruction")

Stochastic normalizing flows for lattice field theory (in session "Generative flow methods")

Summary

Symbolic Distillation of Neural Networks (in session "ML as component of exact algorithms")

TBA (in session "Symmetry equivariant neural networks/informed neural networks")

Teaching how to teach: defining learning samples to detect phase transitions (in session "ML for phase transitions and sign problem mitigation")

The route towards phase transition recognition in Lattice Gauge Theories (in session "EFT, Lattice and ML")

Towards fully bayesian analyses in Lattice QCD (in session "ML for physical interpretation of lattice results")

Variational Autoregressive Networks for Information Theory (in session "Gauge field generation")

Welcome and aims of the workshop

Include materials from selected contributions

Events scheduled on*

2/27/23

2/28/23

3/1/23

3/2/23

3/3/23

Include materials from sessions/contributions scheduled on the selected dates