Fifth Machine Learning in High Energy Physics Summer School 2019

Europe/Berlin
SR4 (DESY)

SR4

DESY

Notkestr. 85, 22607 Hamburg, Germany
Andrey Ustyuzhanin (Yandex School of Data Analysis (RU)) , Isabell Melzer-Pellmann (Deutsches Elektronen-Synchrotron (DE))
Description

The Fifth Machine Learning summer school organised by Yandex School of Data AnalysisLaboratory of Methods for Big Data Analysis of National Research University Higher School of Economics, Hamburg University and DESY will be held at DESY, Hamburg, Germany from the 1st to 10th of July 2019.

The school will cover the relatively young area of data analysis and computational research that has started to emerge in High Energy Physics (HEP). It is known by several names including “Multivariate Analysis”, “Neural Networks”, “Classification/Clusterization techniques”. In more generic terms, these techniques belong to the field of “Machine Learning”, which is an area that is based on research performed in Statistics and has received a lot of attention from the Data Science community.

There are plenty of essential problems in high energy physics that can be solved using Machine Learning methods. These vary from online data filtering and reconstruction to offline data analysis.

Students of the school will receive a theoretical and practical introduction to this new field and will be able to apply acquired knowledge to solve their own problems. Topics ranging from decision trees to deep learning and hyperparameter optimisation will be covered with concrete examples and hands-on tutorials. A special data-science competition will be organised within the school to allow participants to get better feeling of real-life ML applications scenarios.

The expected number of students for the school is 60. The school is aimed at PhD students and postdoctoral researchers, but also open to masters students.

Pre-requisites for participation

Upon completion of the school participants would be able to

  • formulate a HEP-related problem in ML-friendly terms;
  • select quality criteria for a given problem;
  • understand and apply principles of widely-used classification models (e.g. boosting, bagging, BDT, neural networks, etc) to practical cases;
  • optimise features and parameters of a given model in efficient way under given restrictions;
  • select the best classifier implementation amongst a variety of ML libraries (scikit-learn, xgboost, deep learning libraries, etc);
  • understand and apply principles of generative model design;
  • define & conduct reproducible data-driven experiments.

School materials

School materials will be available on github.

Organisers

Partners

AMVA4NP  

Sponsors

We can provide a bit of subsidy for students who are not able to afford the full registration fee out of their own funds. Make sure you apply before the early registration deadline. See registration fee page for details. 

   
INSIGHTS is funded by the European Union’s Horizon 2020 research and innovation programme,
call H2020-MSCA-ITN-2017, under Grant Agreement n. 765710
    • Organisational: Opening words SR4

      SR4

      DESY

      Notkestr. 85, 22607 Hamburg, Germany
      Conveners: Andrey Ustyuzhanin (Yandex School of Data Analysis (RU)) , Miha Zgubic (University of Oxford (GB))
    • Lectures: Introduction: Probability, MLE vs MAP, Inference SR 4 a/b

      SR 4 a/b

      DESY

      Convener: Andrey Ustyuzhanin (Yandex School of Data Analysis (RU))
    • 10:45 AM
      Coffee break SR4

      SR4

      DESY

      Notkestr. 85, 22607 Hamburg, Germany
    • Lecture: Linear models, regression classification SR 4 a/b

      SR 4 a/b

      DESY

      Convener: Alexey Artemov (Yandex)
      • 3
        Lecture: Linear models, regression classification
        Speaker: Alexey Artemov (Yandex)
    • Organisational: Lunch SR4

      SR4

      DESY

      Notkestr. 85, 22607 Hamburg, Germany
    • Seminar: Figures of Merit, overfitting (MLE vs MAP vs AP) SR4

      SR4

      DESY

      Notkestr. 85, 22607 Hamburg, Germany
      Convener: Alexey Artemov (Yandex)
      • 4
        Seminar: Figures of Merit, overfitting (MLE vs MAP vs AP)
        Speaker: Dr Alexey Artemov (Skoltech, HSE)
    • 3:30 PM
      Coffee break SR4

      SR4

      DESY

      Notkestr. 85, 22607 Hamburg, Germany
    • Practice: Competition Introduction SR4

      SR4

      DESY

      Notkestr. 85, 22607 Hamburg, Germany
      Convener: Mr Vladislav Belavin (Yandex School of Data Analysis (RU))
      • 5
        Competition Introduction
        Speaker: Vladislav Belavin (Yandex School of Data Analysis (RU))
    • 6:00 PM
      Welcome reception Canteen Extension

      Canteen Extension

    • 6
      Lecture: Decision tree-based models SR4

      SR4

      DESY

      Notkestr. 85, 22607 Hamburg, Germany
      Speaker: Andrey Ustyuzhanin (Yandex School of Data Analysis (RU))
    • 10:30 AM
      Coffee break SR4

      SR4

      DESY

      Notkestr. 85, 22607 Hamburg, Germany
    • 7
      Seminar: Ensembles of models; bagging, boosting, random forest SR4

      SR4

      DESY

      Notkestr. 85, 22607 Hamburg, Germany
      Speaker: Nikita Kazeev (Yandex School of Data Analysis (RU))
    • Organisational: Lunch SR4

      SR4

      DESY

      Notkestr. 85, 22607 Hamburg, Germany
    • 8
      Lecture: Unsupervised Machine Learning SR4

      SR4

      DESY

      Notkestr. 85, 22607 Hamburg, Germany
      Speaker: Andrey Ustyuzhanin (Yandex School of Data Analysis (RU))
    • 3:30 PM
      Coffee break SR4

      SR4

      DESY

      Notkestr. 85, 22607 Hamburg, Germany
    • 9
      Seminar: Clustering SR4

      SR4

      DESY

      Notkestr. 85, 22607 Hamburg, Germany
      Speaker: Mikhail Hushchyn
    • 10
      Competition time SR4

      SR4

      DESY

      Notkestr. 85, 22607 Hamburg, Germany
    • 11
      Lecture: Introduction into Neural Network models; Multi-layered Perceptron; Backpropagation SR4

      SR4

      DESY

      Notkestr. 85, 22607 Hamburg, Germany
      Speaker: Alexander Panin (Yandex School of Data Analysis (RU))
    • 10:30 AM
      Coffee break SR4

      SR4

      DESY

      Notkestr. 85, 22607 Hamburg, Germany
    • 12
      Seminar: Computing gradient by hand. Pytorch. SR4

      SR4

      DESY

      Notkestr. 85, 22607 Hamburg, Germany
      Speaker: Alexander Panin (Yandex School of Data Analysis (RU))
    • 1:00 PM
      Lunch break Canteen

      Canteen

      DESY

    • 13
      Lecture: Intro to Deep learning; Convolutional Neural Networks SR4

      SR4

      DESY

      Notkestr. 85, 22607 Hamburg, Germany
      Speaker: Alexander Panin (Yandex School of Data Analysis (RU))
    • 3:30 PM
      Coffee break SR4

      SR4

      DESY

      Notkestr. 85, 22607 Hamburg, Germany
    • 14
      Seminar: Image recognition using convolutional neural networks SR4

      SR4

      DESY

      Notkestr. 85, 22607 Hamburg, Germany
      Speaker: Alexander Panin (Yandex School of Data Analysis (RU))
    • 15
      Competition time SR4

      SR4

      DESY

      Notkestr. 85, 22607 Hamburg, Germany
    • 16
      Bayesian methods 1 SR4

      SR4

      DESY

      Notkestr. 85, 22607 Hamburg, Germany
      Speaker: Dr Ekaterina Lobacheva
    • 10:30 AM
      Coffee break SR4

      SR4

      DESY

      Notkestr. 85, 22607 Hamburg, Germany
    • 17
      Bayesian methods 2 SR4

      SR4

      DESY

      Notkestr. 85, 22607 Hamburg, Germany
      Speaker: Dr Ekaterina Lobacheva
    • Organisational: Lunch SR4

      SR4

      DESY

      Notkestr. 85, 22607 Hamburg, Germany
    • 18
      Bayesian neural networks 1 SR4

      SR4

      DESY

      Notkestr. 85, 22607 Hamburg, Germany
      Speaker: Dr Nadezhda Chirkova
    • 3:30 PM
      Coffee break SR4

      SR4

      DESY

      Notkestr. 85, 22607 Hamburg, Germany
    • 19
      Bayesian neural networks 2 SR4

      SR4

      DESY

      Notkestr. 85, 22607 Hamburg, Germany
      Speaker: Dr Nadezhda Chirkova
    • 20
      Lecture: Likelihood free inference SR4

      SR4

      DESY

      Notkestr. 85, 22607 Hamburg, Germany
      Speaker: Dr Gilles Louppe (New York University (US))
    • Lecture: Generative Models (GM); GMM; Probability density estimation (kernel, fitting); RBM; JS GAN; pivot SR4

      SR4

      DESY

      Notkestr. 85, 22607 Hamburg, Germany
      Convener: Maxim Borisyak (Yandex School of Data Analysis (RU))
      • 21
        Lecture: Generative Models (GM); GMM; Probability density estimation (kernel, fitting); RBM; JS GAN; pivot
        Speaker: Maxim Borisyak (Yandex School of Data Analysis (RU))
    • 10:30 AM
      Coffee break SR4

      SR4

      DESY

      Notkestr. 85, 22607 Hamburg, Germany
    • Seminar: Learning to pivot SR4

      SR4

      DESY

      Notkestr. 85, 22607 Hamburg, Germany
      Convener: Maxim Borisyak (Yandex School of Data Analysis (RU))
      • 22
        Seminar: Learning to pivot
        Speaker: Maxim Borisyak (Yandex School of Data Analysis (RU))
    • Organisational: Lunch SR4

      SR4

      DESY

      Notkestr. 85, 22607 Hamburg, Germany
    • 23
      Lecture: Sequence Modelling SR4

      SR4

      DESY

      Notkestr. 85, 22607 Hamburg, Germany
      Speaker: Dr Ekaterina Artemova
    • 3:20 PM
      Coffee break SR4

      SR4

      DESY

      Notkestr. 85, 22607 Hamburg, Germany
    • 24
      Seminar: RNN: GRU + LSTM + Jet recognition SR4

      SR4

      DESY

      Notkestr. 85, 22607 Hamburg, Germany
      Speaker: Dr Ekaterina Artemova
    • Seminar: NN interpretation. Tips & tweaks. SR4

      SR4

      DESY

      Notkestr. 85, 22607 Hamburg, Germany
      Convener: Maxim Borisyak (Yandex School of Data Analysis (RU))
      • 25
        Seminar: NN interpretation. Tips & tweaks.
        Speakers: Alexander Panin (Yandex School of Data Analysis (RU)) , Maxim Borisyak (Yandex School of Data Analysis (RU))
    • 26
      Competition 2 intro + Competition seminar SR4

      SR4

      DESY

      Notkestr. 85, 22607 Hamburg, Germany
      Speaker: Vladislav Belavin (Yandex School of Data Analysis (RU))
    • 27
      Lecture: Causal inference SR4

      SR4

      DESY

      Notkestr. 85, 22607 Hamburg, Germany
      Speaker: Evgeniy Riabenko
    • 10:30 AM
      Coffee break SR4

      SR4

      DESY

      Notkestr. 85, 22607 Hamburg, Germany
    • 28
      Seminar: Causal inference SR4

      SR4

      DESY

      Notkestr. 85, 22607 Hamburg, Germany
      Speaker: Evgeniy Riabenko
    • 1:00 PM
      Lunch - there will be "Belegte Brötchen" (baked rolls) in front of SR 4 a/b SR4

      SR4

      DESY

      Notkestr. 85, 22607 Hamburg, Germany
    • 29
      Lecture: GAN advanced topics: WGAN, Cramer GAN SR4

      SR4

      DESY

      Notkestr. 85, 22607 Hamburg, Germany
      Speaker: Dr Artem Maevskiy (National Research University Higher School of Economics (RU))
    • 3:30 PM
      Coffee break SR4

      SR4

      DESY

      Notkestr. 85, 22607 Hamburg, Germany
    • 30
      DIRC-GAN SR4

      SR4

      DESY

      Notkestr. 85, 22607 Hamburg, Germany
      Speaker: Nikita Kazeev (Yandex School of Data Analysis (RU))
    • 31
      Evening event: Artificial intelligence: Past, Present and Future Auditorium

      Auditorium

      DESY

    • 32
      Lecture: Black-box optimization: Bayesian Optimization, Variational Optimization, Adversarial Optimization SR4

      SR4

      DESY

      Notkestr. 85, 22607 Hamburg, Germany
      Speaker: Maxim Borisyak (Yandex School of Data Analysis (RU))
    • 10:30 AM
      Coffee break SR4

      SR4

      DESY

      Notkestr. 85, 22607 Hamburg, Germany
    • 33
      Seminar: Tuning PYTHIA SR4

      SR4

      DESY

      Notkestr. 85, 22607 Hamburg, Germany
      Speaker: Maxim Borisyak (Yandex School of Data Analysis (RU))
    • 1:00 PM
      Lunch break Canteen

      Canteen

      DESY

    • 34
      Seminar: NN Hyper-parameter optimization, comet SR4

      SR4

      DESY

      Notkestr. 85, 22607 Hamburg, Germany
      Speaker: Andrey Ustyuzhanin (Yandex School of Data Analysis (RU))
    • 3:30 PM
      Coffee break SR4

      SR4

      DESY

      Notkestr. 85, 22607 Hamburg, Germany
    • 35
      Lecture: Dark Machines SR4

      SR4

      DESY

      Notkestr. 85, 22607 Hamburg, Germany
      Speaker: Sascha Caron (Nikhef National institute for subatomic physics (NL))
    • 36
      Seminar: Independence of NN classifier from a continuous parameter SR4

      SR4

      DESY

      Notkestr. 85, 22607 Hamburg, Germany
      Speaker: Miha Zgubic (University of Oxford (GB))
    • 37
      Graph Network in High Energy Physics SR4

      SR4

      DESY

      Notkestr. 85, 22607 Hamburg, Germany
      Speaker: Dr Jean-Roch Vlimant (California Institute of Technology (US))
    • 10:30 AM
      Coffee break SR4

      SR4

      DESY

      Notkestr. 85, 22607 Hamburg, Germany
    • 38
      Organizational info SR4

      SR4

      DESY

      Notkestr. 85, 22607 Hamburg, Germany
      Speaker: Isabell Melzer-Pellmann (Deutsches Elektronen-Synchrotron (DE))
    • 39
      Lecture: Machine Learning and Computer Vision for Particle Imaging Detectors in Neutrino Experiments SR4

      SR4

      DESY

      Notkestr. 85, 22607 Hamburg, Germany
      Speakers: KAZUHIRO TERAO (C) , Dr Kazuhiro Terao (SLAC National Accelerator Laboratory) , Dr Kazuhiro Terao (Columbia University)
    • 12:30 PM
      Lunch break Canteen

      Canteen

      DESY

    • 40
      Lecture: Probabilistic programming SR4

      SR4

      DESY

      Notkestr. 85, 22607 Hamburg, Germany
      Speaker: Lukas Alexander Heinrich (CERN)
    • 41
      Seminar: Probabilistic programming SR4

      SR4

      DESY

      Notkestr. 85, 22607 Hamburg, Germany
      Speaker: Lukas Alexander Heinrich (CERN)
    • 3:45 PM
      Coffee break SR4

      SR4

      DESY

      Notkestr. 85, 22607 Hamburg, Germany
    • 42
      Lecture: Using Bayesian Framework to identify Risks in Project Management SR4

      SR4

      DESY

      Notkestr. 85, 22607 Hamburg, Germany
      Speaker: Sanjay Basu (Oracle)
    • 7:00 PM
      Workshop dinner MS Commodore (Elbe, Starting point: Landungsbrücken 7-9)

      MS Commodore

      Elbe, Starting point: Landungsbrücken 7-9

    • 43
      Machine Learning with Multiscale Dataflow Computing for High Energy Physics-1 SR4

      SR4

      DESY

      Notkestr. 85, 22607 Hamburg, Germany
      Speaker: Voss Nils
    • 10:30 AM
      Coffee break SR4

      SR4

      DESY

      Notkestr. 85, 22607 Hamburg, Germany
    • 44
      Machine Learning with Multiscale Dataflow Computing for High Energy Physics-2 SR4

      SR4

      DESY

      Notkestr. 85, 22607 Hamburg, Germany
      Speaker: Nils Voss
    • 45
      School wrap up SR4

      SR4

      DESY

      Notkestr. 85, 22607 Hamburg, Germany
      Speaker: Andrey Ustyuzhanin (Yandex School of Data Analysis (RU))