Rutgers University Department of Physics and Astronomy

PHYSICS 694, SPRING 2021

ADVANCED TOPICS IN HIGH ENERGY PHYSICS

The topic of this course will be deep learning applications to high energy physics. I will focus primarily on collider physics and the LHC, but if time permits I may also broaden the focus to include other subfields relevant to HEP.

The last few years have seen the deep learning revolution come to HEP and the LHC. New algorithms and new approaches are being proposed to solve a wide array of problems, including jet tagging, event classification, pileup reduction, event generation, calorimeter simulation, and anomaly detection. The goal of this course is to provide an overview of these various deep learning applications at the LHC, with an eye towards current trends in research. Along the way, students will receive a practical introduction to fundamental concepts and methods in machine learning and data science. Hopefully, after taking this semester-long course, students will be able to understand the latest ML4HEP results on the arXiv and possibly even embark on research projects of their own.

ANNOUNCEMENTS

The first meeting of this course will be WEDNESDAY, JANUARY 20, 2021.

GENERAL INFORMATION

Instructor:

Prof. David Shih
Office: Serin E370
Email: dshih@physics.rutgers.edu
Phone: (848) 445-9072
Office hours: By appointment

Lectures: Wednesday 10:20-11:40AM and Friday 3:20-4:40PM, VIRTUAL

Resources:

The Deep Learning Book. Goodfellow, Bengio and Courville (2016).

Prerequisites:

You will be expected to be at least somewhat familiar with python and some of its essential packages (numpy, matplotlib, ...). A background in collider physics would also be helpful, although I will attempt to review the basics in the first few lectures.

You will NOT be required to know ROOT or any physics simulation tools (such as Madgraph, Pythia and Delphes). You will also NOT be required to know in advance any of the deep learning software frameworks such as Keras, Tensorflow and pytorch.

Homeworks: TBD

Exams: TBD

Students with disabilities: Please read here.

LIST OF TOPICS

Here is a list of topics I will aim to cover in the course. This list is incomplete and approximate. Note it is not a syllabus! In particular the order of topics might be different in the course.

LECTURE NOTES

Lecture 1 January 20, 2021

Lecture 2 January 22, 2021

Lecture 3 January 27, 2021 MNIST example notebook

Lecture 4 January 29, 2021 MNIST DNN demo

https://towardsdatascience.com/understanding-the-bias-variance-tradeoff-165e6942b229 Overfitting, underfitting, and bias-variance tradeoff
https://towardsdatascience.com/gradient-descent-algorithm-and-its-variants-10f652806a3 Good description of gradient descent algorithm
https://www.cs.cornell.edu/courses/cs4780/2018fa/lectures/lecturenote07.html More on gradient descent (and vs. Newton's method)

Lecture 5 February 3, 2021

https://ruder.io/optimizing-gradient-descent/ Great description of different gradient descent algorithms
https://brilliant.org/wiki/backpropagation/ Detailed derivation of the backprop algorithm

Lecture 6 February 5, 2021 MNIST DNN multiclass example

http://people.stern.nyu.edu/churvich/Regress/Handouts/Chapt7.pdf I based my proof of the Neyman-Pearson Lemma heavily off of this

Lecture 7 February 10, 2021 CIFAR10 example (UPDATED March 4 to include CNN classifier)

Lecture 8 February 12, 2021

Lecture 9 February 17, 2021

Lecture 10 February 19, 2021 Top and QCD jets

Lecture 11 February 24, 2021

Lecture 12 February 26, 2021

Lecture 13 March 3, 2021 Top and QCD jets 2

Lecture 14 March 5, 2021

Notebook showing how to create centered jet images
Top tagging classifier examples
Community top tagging comparison -- an excellent resource for state-of-the-art in jet tagging with deep learning at the LHC

Lecture 15 March 10, 2021 Top tagging decorrelation

Lecture 16 March 24, 2021 Top tagging decorrelation 2 -- worked exercises, planing, and DisCo

Lecture 17 March 26, 2021

Lecture 18 March 31, 2021 GAN MNIST example

An amazing GAN visualization

Lecture 19 April 2, 2021 WGAN-GP trained on MNIST

Lecture 20 April 7, 2021

Lecture 21 April 9, 2021 Vanilla Autoencoder MNIST example

Lecture 22 April 14, 2021

Lecture 23 April 16, 2021 GUEST LECTURE: Claudius Krause (density estimation and normalizing flows)

Lecture 24 April 21, 2021 Normalizing Flows Tutorial (Authors: Sascha Diefenbacher, Tobias Loesche and Manuel Sommerhalder)

Lecture 25 April 23, 2021

Lecture 26 April 28, 2021 Anomaly Detection Tutorial 1

Lecture 27 April 30, 2021 Anomaly Detection Tutorial 2 Anomaly Detection Tutorial 3

PROBLEM SETS

Problem set 1 due: Friday February 12, 2021

Please send any comments on this page to dshih@physics.rutgers.edu.