Les Houches Summer School Lecture Notes
 a series contained in

SciPost Physics Lecture Notes
Collection 202207: Statistical Physics & Machine learning
The school is aimed primarily at the growing audience of theoretical physicists, applied mathematicians, computer scientists and colleagues from other computational fields interested in machine learning, neural networks, and highdimensional data analysis. We shall cover basics and frontiers of highdimensional statistics, machine learning, theory of computing and statistical learning, and the related mathematics and probability theory. We will put a special focus on methods of statistical physics and their results in the context of current questions and theories related to these problems. Open questions and directions will be discussed as well.
Organizers
 Florent Krzakala (EPFL)
 Lenka ZdeborovĂˇ (EPFL)
Lecturers
 Francis Bach (Inria, ENS): Sumsofsquares: from polynomials to kernels [videos]
 Yasaman Bahri (Google) and Boris Hanin (Princeton): Deep learning at large and infinite width
 Boaz Barak (Harvard): Computational complexity of deep learning: Fundamental limitations and empirical phenomena
 Giulio Biroli (ENS Paris): Highdimensional nonconvex landscapes and gradient descent dynamics
 Michael I. Jordan (Berkeley) On decision, dynamics, incentives, and mechanisms design
 Julia Kempe (NYU): Data, physics and kernels and how can (statistical) physics tools help the DL practitioner
 Yann LeCun (Facebook & NYU): From machine learning to autonomous intelligence
 Marc MĂ©zard (ENS Paris): Belief propagation, messagepassing & sparse models
 Remi Monasson (ENS Paris): Replica method for computational problems with randomness: principles and illustrations
 Andrea Montanari (Stanford): Neural networks from a nonparametric viewpoint
 Sara Solla (Northwestern Univ.): Statistical physics, Bayesian inference and neural information processing
 Haim Sompolinsky (Harvard & Hebrew Univ.): Statistical mechanics of machine learning
 Nathan Srebro (TTI Chicago) Applying statistical learning theory to deep learning
 Eric VandenEijnden (NYU Courant): Benefits of overparametrization in statistical learning, & enhancing MCMC sampling with learning
Dates: from 20220704 to 20220729.
Publications in this Collection
 No Publication has yet been associated to this Collection