# Machine learning for sampling high-dimensional probability distributions in lattice field theory

- Institution: CERN
- Department: EP-IT Data Science Seminars
- Speaker: Phiala Shanahan
- Year: 2023
- Language: English
- Subjects: Computer science
- Source: [CERN](https://videos.cern.ch/record/3007175)
- Licence: [CERN](http://copyright.web.cern.ch)
- Who can watch: Tweens profiles and older (sources give no ratings; placed by Invisible Network from the source's own words)

As machine learning algorithms continue to enable and accelerate physics calculations, the development of problem-specific physics-informed machine learning approaches is becoming more sophisticated, impactful, and important. I will describe recent advances in generative modelling emerging from the challenge of exact sampling from known probability distributions in the context of lattice quantum field theory calculations in particle and nuclear physics. I will discuss in particular flow-based generative models, outline the importance of guarantees of exactness and the incorporation of complex symmetries (e.g., gauge symmetry) into model architectures, and show how this can be achieved.

Phiala Shanahan is an Associate Professor of physics at MIT. Her research group works to understand nuclear physics from the Standard Model through first-principles calculations using tools including lattice field theory, effective field theories, and many-body methods. She received her PhD from the University of Adelaide, spent two years as a postdoctoral fellow at MIT and one year as a joint faculty member at the College of William & Mary and senior staff scientist at the Thomas Jefferson National Accelerator facility, before moving to her current position.

Coffee will be served at 10:30. .

0:00:00 Slide 1

0:02:07 Slide 2

0:03:37 Slide 3

0:05:28 Slide 4

0:06:36 Slide 5

0:08:24 Slide 6

0:10:37 Slide 7

0:12:17 Slide 8

0:14:12 Slide 9

0:15:31 Slide 10

0:16:52 Slide 11

0:18:11 Slide 12

0:19:27 Slide 13

0:21:12 Slide 14

0:24:54 Slide 15

0:27:10 Slide 16

0:28:50 Slide 17

0:31:15 Slide 18

0:33:34 Slide 19

0:34:45 Slide 20

0:36:12 Slide 21

0:38:11 Slide 22

0:39:53 Slide 23

0:41:20 Slide 24

0:43:55 Slide 25

0:46:18 Slide 26

0:47:45 Slide 27

0:49:23 Slide 28

0:51:12 Slide 29

0:52:39 Slide 30

0:55:08 Slide 31

1:00:36 Slide 32

1:02:09 Slide 33

1:03:20 Slide 34

1:05:28 Slide 35

## Lectures

1. [Machine learning for sampling high-dimensional probability distributions in lattice field theory](https://invisiblenetwork.ai/learn/cern/3007175/ab10969c21ee), 1 h 11 min (CERN's player)