ABSTRACT

This talk describes structural results for multi-agent systems when individual agents perform social learning. Three specific examples are considered.  The first example deals with the so called constrained optimal social learning problem where the onset of herding is delayed by agents sharing full information The second example deals with change detection when individual agents perform social learning.

The third example highlights some recent (but incomplete work) in social networks where diffusion approximations are made resulting in a controlled Markovian system. Learning of correlated equilibria is considered as an example.

 

BIO

Dr Krishnamurthy’s current research interests include:

• statistical signal processing for social  networks and multimedia networks

• computational game theory, stochastic optimization and scheduling   in radar and surveillance systems

• stochastic dynamical systems for modeling of proteins and biosensors

• social learning and social sensing

 

Vikram is a Fellow of the IEEE. He was awarded an honorary doctorate from KTH (Royal Institute of Technology), Stockholm, Sweden in 2013.