Sharan Vaswani


Sharan is a postdoc at the Mila-Quebec Artificial Intelligence Institute, where he works with Simon Lacoste-Julien. His current research interests are in stochastic optimization and its interplay with generalization in modern machine learning. He is also interested in designing better algorithms for sequential decision-making under uncertainty.

From 2015 to2018, he was a PhD student in computer science at the University of British Columbia (UBC). He was co-supervised by Laks Lakshmanan and Mark Schmidt. His PhD research was on "Structured Bandits and Applications", where he considered problems involving decision-making under uncertainty for applications in social networks and recommender systems. Prior to that, he completed his MSC in computer science from UBC in 2015. He was supervised by Laks Lakshmanan and worked on the online and adaptive variants of the influence maximization problem in social networks. Before coming to UBC, he was a research engineer in the parallel systems group at Siemens Corporate Research in Bangalore. He obtained his bachelor's degree in computer science from the Birla Institute of Technology and Science Pilani, India in 2012.

Program Visits

Theory of Reinforcement Learning, Fall 2020, Visiting Postdoc