263-5300-00L  Guarantees for Machine Learning

SemesterFrühjahrssemester 2020
DozierendeF. Yang
Periodizitätjährlich wiederkehrende Veranstaltung
LehrspracheEnglisch



Lehrveranstaltungen

NummerTitelUmfangDozierende
263-5300-00 VGuarantees for Machine Learning
Special selection process. Preference is given to Masters and Doctorate students. If need be other criteria are degree program and previous courses taken.
2 Std.
Mi08:15-10:00CAB G 51 »
F. Yang
263-5300-00 AGuarantees for Machine Learning2 Std.F. Yang

Katalogdaten

KurzbeschreibungThis course teaches classical and recent methods in statistics and optimization commonly used to prove theoretical guarantees for machine learning algorithms. The knowledge is then applied in project work that focuses on understanding phenomena in modern machine learning.
LernzielThis course is aimed at advanced master and doctorate students who want to understand and/or conduct independent research on theory for modern machine learning. For this purpose, students will learn common mathematical techniques from statistical learning theory. In independent project work, they then apply their knowledge and go through the process of critically questioning recently published work, finding relevant research questions and learning how to effectively present research ideas to a professional audience.
InhaltThis course teaches some classical and recent methods in statistical learning theory aimed at proving theoretical guarantees for machine learning algorithms, including topics in

- concentration bounds, uniform convergence
- high-dimensional statistics (e.g. Lasso)
- prediction error bounds for non-parametric statistics (e.g. in kernel spaces)
- minimax lower bounds
- regularization via optimization

The project work focuses on active theoretical ML research that aims to understand modern phenomena in machine learning, including but not limited to

- how overparameterization could help generalization ( interpolating models, linearized NN )
- how overparameterization could help optimization ( non-convex optimization, loss landscape )
- complexity measures and approximation theoretic properties of randomly initialized and
trained NN
- generalization of robust learning ( adversarial robustness, standard and robust error tradeoff )
- prediction with calibrated confidence ( conformal prediction, calibration )
Voraussetzungen / BesonderesIt’s absolutely necessary for students to have a strong mathematical background (basic real analysis, probability theory, linear algebra) and good knowledge of core concepts in machine learning taught in courses such as “Introduction to Machine Learning”, “Regression”/ “Statistical Modelling”. It's also helpful to have heard an optimization course or approximation theoretic course. In addition to these prerequisites, this class requires a certain degree of mathematical maturity—including abstract thinking and the ability to understand and write proofs.

Leistungskontrolle

Information zur Leistungskontrolle (gültig bis die Lerneinheit neu gelesen wird)
Leistungskontrolle als Semesterkurs
ECTS Kreditpunkte5 KP
PrüfendeF. Yang
Formbenotete Semesterleistung
PrüfungsspracheEnglisch
RepetitionRepetition nur nach erneuter Belegung der Lerneinheit möglich.
Zusatzinformation zum PrüfungsmodusLast cancellation/deregistration date for this graded semester performance: second Friday in March! Please note that after that date no deregistration will be accepted and a "no show" will appear on your transcript.

one Midterm exam (50%)
Homework (10%)
Course project (40%)

Lernmaterialien

 
HauptlinkInformation
Es werden nur die öffentlichen Lernmaterialien aufgeführt.

Gruppen

Keine Informationen zu Gruppen vorhanden.

Einschränkungen

PlätzePlätze beschränkt. Spezielles Auswahlverfahren.
WartelisteBis 08.03.2020
BelegungsendeBelegung nur bis 01.03.2020 möglich

Angeboten in

StudiengangBereichTyp
Cyber Security MasterWahlfächerWInformation
Data Science MasterWählbare KernfächerWInformation
Doktorat Departement InformatikLehrangebot Doktorat und PostdoktoratWInformation
Elektrotechnik und Informationstechnologie MasterVertiefungsfächerWInformation
Elektrotechnik und Informationstechnologie MasterEmpfohlene FächerWInformation
Informatik MasterWahlfächer der Vertiefung in Information SystemsWInformation
Informatik MasterWahlfächer der Vertiefung General StudiesWInformation
Informatik MasterWahlfächer der Vertiefung in Computational ScienceWInformation
Mathematik BachelorAuswahl: Weitere GebieteWInformation
Mathematik MasterAuswahl: Weitere GebieteWInformation
Statistik MasterStatistische und mathematische FächerWInformation