VVZ API is not affiliated with ETH Zurich. Data might be outdated or incorrect. Please view the official ETHZ Vorlesungsverzeichnis for binding information.

263-4508-00L 10 Credits MSC , WBZ D-ITET , D-INFK , D-MATH

Algorithmic Foundations of Data Science

Lecturers & Examiners: Prof. Dr. David Steurer
VVZ CR 4.04

Last Updated: 2026-06-03 00:14:09

Abstract

This course provides rigorous theoretical foundations for the design and mathematical analysis of efficient algorithms that can solve fundamental tasks relevant to data science.

Objective

We consider various statistical models for basic data-analytical tasks, e.g., (sparse) linear regression, principal component analysis, matrix completion, community detection, and clustering. Our goal is to design efficient (polynomial-time) algorithms that achieve the strongest possible (statistical) guarantees for these models. Toward this goal we learn about a wide range of mathematical techniques from convex optimization, linear algebra (especially, spectral theory and tensors), and high-dimensional statistics. We also incorporate adversarial (worst-case) components into our models as a way to reason about robustness guarantees for the algorithms we design.

Content

Strengths and limitations of efficient algorithms in (robust) statistical models for the following (tentative) list of data analysis tasks: - (sparse) linear regression - principal component analysis and matrix completion - clustering and Gaussian mixture models - community detection

Resources

Lecture Notes

To be provided during the semester

Literature

High-Dimensional Statistics A Non-Asymptotic Viewpoint by Martin J. Wainwright

Learning Materials (Links)

General Information

Language
English
Levels
MSC , WBZ
Frequency
Yearly recurring

Examination

Type
session examination
Mode
written 240 minutes
Aids
None
During the course of the semester, we will assign two graded homeworks as compulsory continuous performance assessments, accounting together for 30% of the final grade (15% for each graded homework). Each graded homework consists of multiple parts that will be released at different points in the semester.The written session examination accounts for the remaining 70% of the final grade.

Course Components

Type Title Time & Place Hours
lecture Algorithmic Foundations of Data Science
  • Tue 10:15-12:00 (HG D 7.1)
  • Tue 13:15-14:00 (HG E 1.1)
3 h weekly
exercise Algorithmic Foundations of Data Science
  • Fri 12:15-14:00 (CAB G 11)
2 h weekly
independent project Algorithmic Foundations of Data Science No time listed 4 h weekly

Offered In