• Girolami, M., & Calderhead, B. (2011). Riemann manifold langevin and hamiltonian monte carlo methods. Journal of the Royal Statistical Society: Series B (Statistical Methodology), 73(2), 123-214. pdf

  • Edelman, A., Arias, T. A., & Smith, S. T. (1998). The geometry of algorithms with orthogonality constraints. SIAM journal on Matrix Analysis and Applications, 20(2), 303-353. pdf

  • Bronstein, M. M., Bruna, J., LeCun, Y., Szlam, A., & Vandergheynst, P. (2017). Geometric deep learning: going beyond euclidean data. IEEE Signal Processing Magazine, 34(4), 18-42. pdf

Software and Jupyter lab

We will use the programming language Python. We will share a series of jupyter notebooks that walk students through the fundamentals of Riemannian methods using the librairies:
  • Geoopt Python package
  • Geomstats Python package
  • Pymanopt Python package
  • Manopt MATLAB package

  • Discussions and Grading


    We use Piazza to allow you to get help efficiently from both your classmates and the instructors. Please post your questions about the course material and course logistics to Piazza so that everyone can benefit from the answer. We also highly encourage you to answer your classmates' questions whenever possible – you will get extra practice with the material and receive feedback from the course staff about your answers. More guidelines about posting on Piazza are available on the Piazza page.


    We use Gradescope to submit homeworks and post corrections. The final project will also be submitted on Gradescope.