Seminars
View all Seminars | Download ICal for this eventLearning and Inference in AI: Complementing Empirical Risk Minimization with a Distributional Perspective
Series: CSA Faculty Colloquium
Speaker: Prof. Chiranjib Bhattacharyya, Professor, Dept. of CSA IISc.
Date/Time: Oct 04 16:00:00
Location: CSA Auditorium, (Room No. 104, Ground Floor)
Abstract:
Learning Models from large volumes from Data poses significant computational challenges. In Empirical Risk Minimization(ERM) based formulations each data point becomes a constraint leading to increased computational burden on the optimizer. However, in Statistics, as more data is observed it should be easier to learn the model.
In this talk we will exhibit several alternative formulations which tries to wrestle with this conundrum by complementing the ERM based formulations with Distributional perspectives. These formulations yield new approaches to both classical and contemporary problems ranging from
learning with missing values to inference problems in AI.
Speaker Bio:
Chiranjib Bhattacharyya is currently Tata Chem Professor in the Department of Computer Science and Automation, Indian Institute of Science. His research interests are in foundations of Machine Learning, Optimisation and their applications to Industrial problems. He has authored numerous papers in leading journals and conferences in Machine Learning. Some of his results have won best paper awards.
He joined the Department of CSA, IISc, in 2002 as an Assistant Professor. Prior to joining the Department he was a postdoctoral fellow at UC Berkeley. He holds BE and ME degrees, both in Electrical Engineering,
from Jadavpur University and the Indian Institute of Science, respectively, and completed his PhD from the Department of Computer Science and Automation, Indian Institute of Science. He is fellow of Indian Academy of Engineering and Indian Academy of Sciences.
For more information about research work from his group please see http://mllab.csa.iisc.ac.in.
Host Faculty: Prof. Gugan C.M. Thoppe