University of Southern California

ISI Site Signature

Aram Galstyan
 Project Leader 
 Information Sciences Institute 
 Research Associate Professor 
 Department of Computer Science 
 University of Southern California 
  Aram Galstyan is a Project Leader at the Information Sciences Institute and a Research Associate Professor in the USC Viterbi School of Engineering's Computer Science Department. His current research focuses on statistical mechanics based approaches to inference and learning, statistical models of complex networks, and social network analysis. His other research interests include mathematical modeling of complex adaptive systems, emergent coordination in robotic swarms, and learning and adaptation in multi-agent systems.  
 Research Interests  
  Artificial Intelligence: machine learning, graphical models, semi-supervised learning, statistical mechanics of inference and learning.  
  Complex Networks: Statistical models of co-evolving networks, staitsical mechanics of networks, social network modeling and analysis, dynamical processes in networks.  
  Multi-agent systems: emergent phenomena in MAS, learning and adaptation in MAS, swarm robtics.  
 Recent News  
  May 2015  
  Our paper "Estimating Mutual Information by Local Gaussian Approximation" has been accepted to UAI'15.  
  March 2015  
  Our team was the only one to achieve perfect accuracy in DARPA's Twitter Influence Bot Detection challange.  
  January 2015  
  Two of our papers, "Maximally Informative Hierarchical Representations of High-Dimensional Data", and "Efficient Estimation of Mutual Information for Strongly Dependent Variables", have been accepted to AISTATS'15.  
  September 2014  
  Our paper " Discovering Structure in High-Dimensional Data Through Correlation Explanation" has been accepted to NIPS'14'.