227-0434-10L  Mathematics of Information

SemesterFrühjahrssemester 2021
DozierendeH. Bölcskei
Periodizitätjährlich wiederkehrende Veranstaltung


227-0434-10 VMathematics of Information3 Std.
Do09-12HG D 3.2 »
H. Bölcskei
227-0434-10 UMathematics of Information2 Std.
Mo14-16HG D 3.2 »
H. Bölcskei
227-0434-10 AMathematics of Information2 Std.H. Bölcskei


KurzbeschreibungThe class focuses on mathematical aspects of

1. Information science: Sampling theorems, frame theory, compressed sensing, sparsity, super-resolution, spectrum-blind sampling, subspace algorithms, dimensionality reduction

2. Learning theory: Approximation theory, greedy algorithms, uniform laws of large numbers, Rademacher complexity, Vapnik-Chervonenkis dimension
LernzielThe aim of the class is to familiarize the students with the most commonly used mathematical theories in data science, high-dimensional data analysis, and learning theory. The class consists of the lecture, exercise sessions with homework problems, and of a research project, which can be carried out either individually or in groups. The research project consists of either 1. software development for the solution of a practical signal processing or machine learning problem or 2. the analysis of a research paper or 3. a theoretical research problem of suitable complexity. Students are welcome to propose their own project at the beginning of the semester. The outcomes of all projects have to be presented to the entire class at the end of the semester.
InhaltMathematics of Information

1. Signal representations: Frame theory, wavelets, Gabor expansions, sampling theorems, density theorems

2. Sparsity and compressed sensing: Sparse linear models, uncertainty relations in sparse signal recovery, super-resolution, spectrum-blind sampling, subspace algorithms (ESPRIT), estimation in the high-dimensional noisy case, Lasso

3. Dimensionality reduction: Random projections, the Johnson-Lindenstrauss Lemma

Mathematics of Learning

4. Approximation theory: Nonlinear approximation theory, best M-term approximation, greedy algorithms, fundamental limits on compressibility of signal classes, Kolmogorov-Tikhomirov epsilon-entropy of signal classes, optimal compression of signal classes

5. Uniform laws of large numbers: Rademacher complexity, Vapnik-Chervonenkis dimension, classes with polynomial discrimination
SkriptDetailed lecture notes will be provided at the beginning of the semester.
Voraussetzungen / BesonderesThis course is aimed at students with a background in basic linear algebra, analysis, statistics, and probability.

We encourage students who are interested in mathematical data science to take both this course and "401-4944-20L Mathematics of Data Science" by Prof. A. Bandeira. The two courses are designed to be complementary.

H. Bölcskei and A. Bandeira


Information zur Leistungskontrolle (gültig bis die Lerneinheit neu gelesen wird)
Leistungskontrolle als Semesterkurs
ECTS Kreditpunkte8 KP
PrüfendeH. Bölcskei
RepetitionDie Leistungskontrolle wird in jeder Session angeboten. Die Repetition ist ohne erneute Belegung der Lerneinheit möglich.
Prüfungsmodusschriftlich 180 Minuten
Zusatzinformation zum PrüfungsmodusThe written final exam (180 minutes) will contribute 75% towards the final grade. The remaining 25% will be awarded for a graded student project in the form of a group literature review. A pass grade in this project is a prerequisite for admission to the exam (compulsory continuous performance assessment). Students re-sitting the exam can decide at the beginning of the semester if they want to also repeat the student project (if previously passed).
Hilfsmittel schriftlichLecture and exercise notes allowed. Electronic devices (laptops, calculators, cellphones, etc...) NOT allowed.
Diese Angaben können noch zu Semesterbeginn aktualisiert werden; verbindlich sind die Angaben auf dem Prüfungsplan.


HauptlinkCourse Website
Es werden nur die öffentlichen Lernmaterialien aufgeführt.


Keine Informationen zu Gruppen vorhanden.


Keine zusätzlichen Belegungseinschränkungen vorhanden.

Angeboten in

Data Science MasterInformation and LearningWInformation
Doktorat Departement Informationstechnologie und ElektrotechnikLehrangebot Doktorat und PostdoktoratWInformation
Doktorat Departement MathematikGraduate School / GraduiertenkollegWInformation
Elektrotechnik und Informationstechnologie MasterKernfächerWInformation
Elektrotechnik und Informationstechnologie MasterVertiefungsfächerWInformation
Elektrotechnik und Informationstechnologie MasterAdvanced Core CoursesWInformation
Elektrotechnik und Informationstechnologie MasterEmpfohlene FächerWInformation
Informatik MasterWahlfächerWInformation
Mathematik MasterAuswahl: Weitere GebieteWInformation
Physik MasterAllgemeine WahlfächerWInformation
Quantum Engineering MasterWahlfächerWInformation
Rechnergestützte Wissenschaften MasterWahlfächerWInformation
Statistik MasterStatistische und mathematische FächerWInformation
Statistik MasterFachbezogene WahlfächerWInformation