LinkedIn Twitter
Teaching and Supervision

Online Teaching Material

  • 2010-: Institut Mines-Télécom Atlantique, Brest, lectures (in French) on nonstationary processes (Mathematical and Computational Engineering Lectures).
    My 3rd year lectures on nonstationary processes for the academic year 2020-2021 will take place in March 2021. They have been quite rewritten from scratch, after reviewing a long series of papers and books (over 70 and counting) on these issues for Mathematical Reviews®. The new section on deep learning and AI is obviously expanding. The writing of the book supporting these lectures is in progress.
    List of past lectures for the academic year 2018-2019:
    • Lecture 1 (Tuesday 10th January 2019): Volatility models. GARCH model: definition, properties, dependence structure, QML estimation. Slides
    • Lecture 2 (Friday 11th January 2019): Exponential GARCH model. Bootstrap methods and their application to model-free prediction and inference of univariate models. Multivariate models. Change-point models. Slides
    • Lecture 3 (Monday 25th February 2019): Long-range dependent and multifractal volatility models. Wavelet analysis of volatility processes. Slides
    • Lecture 4 (Tuesday 26th February 2019): Volatility estimation of high frequency time series. Deep Learning: convolutional, recurrent and hybrid architectures. Slides
  • 2009: Aarhus University, PhD lectures, based on the draft version of the book Large Sample Inference for Long Memory Processes (2012) Imperial College Press. In 2013, I wrote the review of this book for Mathematical Reviews®. If you are a MathSciNet subscriber, you could read this review from my  author profile
    Additional material not covered in that book: Slides
  • 2006-2007: Ensae, lectures (in French) on Long-range dependence and change-points, Applications to univariate and multivariate financial time series,
    • Leçon 1 : Processus fortement dépendants, Transparents
    • Leçon 2 : Tests de détection de longue portée et estimateurs du paramètre de longue portée, Transparents
    • Leçon 3 : Tests de détection de ruptures, Transparents
    • Leçon 4 : Méthodes statistiques robustes aux ruptures, Transparents
    • Leçon 5 : Modèles multivariés, Transparents
  • 1993-1996: Lectures on optimization techniques with Maple. I have typed a 200 pages document, that obviously needs to be upgraded.

Machine Learning and AI

Computing Science Resources

  • The first class requires a good working knowledge of R.
    Since the academic year 2016-2017, students undertaking their dissertation on Machine Learning, deep learning, etc., are using either Python with the PyTorch, TensorFlow, and scikit-learn libraries, or Torch for R.
    The efficiency of the running of Python programs is substantially improved by calling them within a Julia program.
  • Some statistical procedures are using Octave, a matrix oriented programming language for numerical computing, the syntax of which is similar to Matlab, up to some changes in the syntax of a few functions.
  • The C++ programming language is still the most powerful language. Valgrind is a useful tool for memory leak debugging, profiling, etc.
    NLopt is a free/open-source library for nonlinear optimization, callable from C, C++, Fortran, Python, Julia, R, Octave, and Matlab programs.
  • Donald Knuth's home page. Don Knuth is the author of the celebrated books: The Art of Computer Programming You can find there everything important on semi-numerical and numerical algorithms, TeX etc.
  • The Digital Library of Mathematical Functions of the National Institute of Standards and Technology (NIST); See A special functions handbook for the digital age, R. Boisvert, C.W. Clark, D. Lozier, and F. Olver, Notices of the American Mathematical Society (2011), vol 58, 905-911, Pdf file. This new online library supersedes the celebrated book by M. Abramowitz and I. Stegun: the Handbook of Mathematical Functions.
    The NIST Statistical Reference Datasets (NIST StRD) for assessing the numerical accuracy of statistical software packages. This database is very useful for checking parts of statistical procedures.
    Useful information on the issue of numerical accuracy of statistical software packages is available at B.D. McCullough's web page.
  • BOINC, the Berkeley Open Infrastructure for Network Computing, is an open-source software for volunteer and grid computing. BOINC projects are covering several fields: physics, astronomy, mathematics, biology, artificial intelligence, cryptography, computer science, etc. If your project is computationally very intensive, and intellectually attractive, you can transform it into a BOINC project.

Other Teaching and Supervision Resources

Updated January 2, 2021.