Advanced Seminar: Statistical physics of disordered systems, information, and inference




This advanced seminar accompanies the lecture course Statistical physics of disordered systems, information, and inference. Topics will be taken from statistical modelling, machine learning, and communication and will be developed together with the participants.

• introduction to probability and information theory
• information theory and the foundations of statistical physics, the principle of maximum entropy
• typical and rare events, the source coding theorem
• disordered systems: introduction to spin glass theory
• statistical inference: the basics of data science
• outlook: inverse problems, the inverse Ising problem

The seminar is part of the area of specialization "Statistical and biological physics" of the Master in physics.

Times and places

The seminar takes place Tuesdays 14:00-15:30 in Seminar Room 1 of the new theory building, the first meeting will be on 4.4. There will be no online-variant of the seminar.

Literature

Cover and Thomas, Elements of Information Theory (Wiley)
MacKay, Information theory, Inference and Learning Algorithms (CUP)
Mézard and Montanari, Information, Physics, and Computation (OUP)

Additional literature will be discussed during the course.




Picture: Confidence region for the family of support vector machines endowed with hyperbolic tangent profile function, by B. Apolloni, S. Bassis, D. Malchiodi, CC BY-SA 3.0, via Wikimedia Commons