Overview

Welcome to the Learning & Adaptive Systems Group at the Department of Computer Science at ETH Zurich. The group is led by Andreas Krause.

Our research is in learning and adaptive systems that actively acquire information, reason and make decisions in large, distributed and uncertain domains, such as sensor networks and the Web. The theoretical aspects include statistical machine learning (online, active, large-scale, ...), probabilistic reasoning and optimization (in particular submodular and non-convex optimization). We devise new algorithms, build models, analyze large and complex data sets and develop systems that can automatically acquire and reason about highly uncertain information. Our application domains include community seismic and traffic sensing, computational sustainability, optimal experimental design and information gathering on the web. See more details here.

News:

• IJCAI-JAIR Best Paper Runner-Up Prize 2012 for our paper ``Optimal Value of Information in Graphical Models'' with Carlos Guestrin
• Invited tutorial on submodular optimization at LION 2012 [pptx,pdf]
• The videos for our NIPS 2011 workshop on Discrete Optimization in Machine Learning (DISCML): Uncertainty, Generalization and Feedback are online.
• Our group will be presenting three papers and a demo at NIPS!
• Our paper on Dynamic Resource Allocation in Conservation Planning receives the Outstanding Paper Award at AAAI 2011!
• Matthew Faulkner received the Demetriades - Tsafka – Kokkalis prize in the area of Seismo-Engineering, Prediction, and Protection.
  
• Pete Trautman selected as presenter at TEDxCaltech.
  
• Andreas Krause invited as speaker at the National Academy of Sciences' Kavli Frontiers 2010 meeting.
  
• Videos of our NIPS 2010 Workshop on Discrete Optimization in Machine Learning are online.
  
• Our paper on Inferring Networks of Diffusion received a Best Research Paper Award Honorable Mention at KDD 2010!
• Andreas Krause received an NSF CAREER award!
• Andreas Krause received an award from the Okawa Foundation
• Cover feature in IEEE Computer Magazine on "Optimizing Sensing from Water to the Web"
• Best Research Paper award from the ASCE Journal of Water Resources Planning and Management
• Check out our Matlab toolbox for optimizing submodular functions