Lecture

Spike Wigner Model

Graph Chat

Chat with Graph Search

Ask any question about EPFL courses, lectures, exercises, research, news, etc. or try the example questions below.

DISCLAIMER: The Graph Chatbot is not programmed to provide explicit or categorical answers to your questions. Rather, it transforms your questions into API requests that are distributed across the various IT services officially administered by EPFL. Its purpose is solely to collect and recommend relevant references to content that you can explore to help you answer your questions.

In course

PHYS-642: Statistical physics for optimization & learning

This course covers the statistical physics approach to computer science problems, with an emphasis on heuristic & rigorous mathematical technics, ranging from graph theory and constraint satisfaction to inference to machine learning, neural networks and st ...

Description

This lecture delves into the Spike Wigner model, focusing on the concept of a Digner spike matrix and its perturbation. The instructor explains the implications of observing matrices in this model, the fundamental theorems related to quantum matrices, and the phase transition phenomenon. The lecture also covers the Bayesian denoising approach, the state evolution, and the analysis of the optimal denoiser. The discussion extends to the VESA phenomenon, the fixed points of algorithms, and the comparison between spectral methods and Bayesian approaches in terms of mean square error. The lecture concludes with a look at the phase diagram for the optimal denoiser and the implications of signal sparsity in machine learning.

Instructors (2)

Lenka Zdeborová

Lenka Zdeborová is a Professor of Physics and of Computer Science in École Polytechnique Fédérale de Lausanne where she leads the Statistical Physics of Computation Laboratory. She received a PhD in physics from University Paris-Sud and from Charles University in Prague in 2008. She spent two years in the Los Alamos National Laboratory as the Director's Postdoctoral Fellow. Between 2010 and 2020 she was a researcher at CNRS working in the Institute of Theoretical Physics in CEA Saclay, France. In 2014, she was awarded the CNRS bronze medal, in 2016 Philippe Meyer prize in theoretical physics and an ERC Starting Grant, in 2018 the Irène Joliot-Curie prize, in 2021 the Gibbs lectureship of AMS. She is an editorial board member for Journal of Physics A, Physical Review E, Physical Review X, SIMODS, Machine Learning: Science and Technology, and Information and Inference. Lenka's expertise is in applications of concepts from statistical physics, such as advanced mean field methods, replica method and related message-passing algorithms, to problems in machine learning, signal processing, inference and optimization. She enjoys erasing the boundaries between theoretical physics, mathematics and computer science.

Florent Gérard Krzakala

Official source

Related concepts (32)

Mean squared error

In statistics, the mean squared error (MSE) or mean squared deviation (MSD) of an estimator (of a procedure for estimating an unobserved quantity) measures the average of the squares of the errors—that is, the average squared difference between the estimated values and the actual value. MSE is a risk function, corresponding to the expected value of the squared error loss. The fact that MSE is almost always strictly positive (and not zero) is because of randomness or because the estimator does not account for information that could produce a more accurate estimate.

Objections to evolution

Objections to evolution have been raised since evolutionary ideas came to prominence in the 19th century. When Charles Darwin published his 1859 book On the Origin of Species, his theory of evolution (the idea that species arose through descent with modification from a single common ancestor in a process driven by natural selection) initially met opposition from scientists with different theories, but eventually came to receive overwhelming acceptance in the scientific community.

Root-mean-square deviation

The root-mean-square deviation (RMSD) or root-mean-square error (RMSE) is a frequently used measure of the differences between values (sample or population values) predicted by a model or an estimator and the values observed. The RMSD represents the square root of the second sample moment of the differences between predicted values and observed values or the quadratic mean of these differences. These deviations are called residuals when the calculations are performed over the data sample that was used for estimation and are called errors (or prediction errors) when computed out-of-sample.

Rejection of evolution by religious groups

Recurring cultural, political, and theological rejection of evolution by religious groups exists regarding the origins of the Earth, of humanity, and of other life. In accordance with creationism, species were once widely believed to be fixed products of divine creation, but since the mid-19th century, evolution by natural selection has been established by the scientific community as an empirical scientific fact.

Errors and residuals

In statistics and optimization, errors and residuals are two closely related and easily confused measures of the deviation of an observed value of an element of a statistical sample from its "true value" (not necessarily observable). The error of an observation is the deviation of the observed value from the true value of a quantity of interest (for example, a population mean). The residual is the difference between the observed value and the estimated value of the quantity of interest (for example, a sample mean).

Related lectures (64)

Proof Technique for the Spiked Model

Covers a proof technique for the spiked model using matrix-based calculations and state evolution.

Random Field Ising Model: Overview and Analysis

Provides an in-depth analysis of the Random Field Ising Model, covering model description, free entropy, and mean field algorithm.

Evolution of Density Matrices

Explores the evolution of density matrices in quantum optics, emphasizing super-operators and completely positive maps.

Applications of GAMP

Delves into applying the GAMP algorithm to simplify the lasso problem and analyze optimization challenges in neural networks.

Overfitting in Supervised Learning: Case Studies and Techniques