Lenka Zdeborová

EPFL SB IPHYS SPOC1
BSP 722 (Cubotron UNIL)
Rte de la Sorge
CH-1015 Lausanne

EPFL IC IINFCOM SPOC2
BC 405 (Bâtiment BC)
Station 14
CH-1015 Lausanne

vCard
Administrative data

Teaching & PhD

Teaching

Physics

PhD Programs

Doctoral Program in Physics

Doctoral program in computer and communication sciences

Courses

Machine learning for physicists

* Examples and types of problems that machine learning can solve. * Linear regression in matrix notation. The concept of prediction, estimation. Least squares method. High-dimensional underdetermined problems and the concept of regularization aka ridge regression. Polynomial regression. The concept of bias and variance trade-off and overfitting. Usage of train, validation and test sets.

Statistical physics of computation

This course covers the statistical physics approach to computer science problems ranging from graph theory and constraint satisfaction to inference and machine learning. In particular the replica and cavity methods, message passings algorithms, and analysis of the related phase transitions.

Statistical physics for optimization & learning

(Coursebook not yet approved by the section)

Lecture series on scientific machine learning

(Coursebook not yet approved by the section)