From 2 November 2020, the autumn semester 2020 will take place online. Exceptions: Courses that can only be carried out with on-site presence. Please note the information provided by the lecturers via e-mail.
Many scientific and commercial applications require insights from massive, high-dimensional data sets. This courses introduces principled, state-of-the-art techniques from statistics, algorithms and discrete and convex optimization for learning from such large data sets. The course both covers theoretical foundations and practical applications.
Many scientific and commercial applications require us to obtain insights from massive, high-dimensional data sets. In this graduate-level course, we will study principled, state-of-the-art techniques from statistics, algorithms and discrete and convex optimization for learning from such large data sets. The course will both cover theoretical foundations and practical applications.
Topics covered: - Dealing with large data (Data centers; Map-Reduce/Hadoop; Amazon Mechanical Turk) - Fast nearest neighbor methods (Shingling, locality sensitive hashing) - Online learning (Online optimization and regret minimization, online convex programming, applications to large-scale Support Vector Machines) - Multi-armed bandits (exploration-exploitation tradeoffs, applications to online advertising and relevance feedback) - Active learning (uncertainty sampling, pool-based methods, label complexity) - Dimension reduction (random projections, nonlinear methods) - Data streams (Sketches, coresets, applications to online clustering) - Recommender systems
Prerequisites / Notice
Prerequisites: Solid basic knowledge in statistics, algorithms and programming. Background in machine learning is helpful but not required.
Performance assessment information (valid until the course unit is held again)