BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Memento EPFL//
BEGIN:VEVENT
SUMMARY:Interactive Machine Learning via Adaptive Submodularity
DTSTART:20140611T140000
DTSTAMP:20260430T043457Z
UID:a4a77133eefc01c20d9d8b50c58db39ecb50323c7b69cc7dcad28078
CATEGORIES:Conferences - Seminars
DESCRIPTION:Andreas KRAUSE\, ETH Zürich\nHow can people and machines coop
 erate to gain insight and discover useful information from complex data se
 ts?  A central challenge lies in optimizing the interaction\, which leads
  to difficult sequential decision problems under uncertainty.  In this ta
 lk\, I will introduce the new concept of adaptive submodularity\, generali
 zing the classical notion of submodular set functions to adaptive policies
 . We prove that if a problem satisfies this property\, a simple adaptive g
 reedy algorithm is guaranteed to be competitive with the optimal policy.\n
 The concept allows to recover\, generalize and extend existing results in 
 diverse domains including active learning\, resource allocation and social
  network analysis. I will show results on several real-world applications\
 , ranging from interactive content search over image categorization in cit
 izen science to biodiversity monitoring via conservation drones.
LOCATION:BC 420 https://plan.epfl.ch/?room==BC%20420
STATUS:CONFIRMED
END:VEVENT
END:VCALENDAR