Projects per year
My core research is at the intersection of statistics, machine learning and optimisation methods. My current research is focussed on modelling data with complex high dimensional network structure and provide methodology for estimating the corresponding structure using tools from nonparametric statistics, graphical models and high dimensional inference. The emphasis is placed on developing new theoretical techniques and computational tools for network problems and applying the corresponding methodology in many fields, including biomedical and social science research, where network modelling and analysis plays an exceedingly important role.
As a mathematical Statistician I am also interested in high dimensional Inference in regression models and understanding the theoretical insights in the modern "big data" framework. The development of novel algorithms along with concrete theoretical results would enable practitioners to use them in many complex real world problems. I have a recent interest also in different optimization methods and especially understanding distributed/parallel computing with large heterogeneous data. These also include fast choice of tuning parameters in optimization algorithms and their implications in the proposed inference.
Statistics, Doctor of Science, University of Michigan
Award Date: 21 Aug 2015
Statistics, Master in Science, Indian Statistical Institute, Kolkata
Award Date: 15 Jul 2010
Statistics, Bachelor of Science, University of Calcutta
Award Date: 12 Jun 2008
30/09/19 → 31/08/20
Project: Research-related funding
3/06/19 → 30/06/19
Project: UK charity
Roy, S., 17 Mar 2020, In: Annals of the Institute of Statistical Mathematics.
Research output: Contribution to journal › Article › peer-reviewFile1 Citation (Scopus)13 Downloads (Pure)
Roy, S., Nunes, M., Lorenz, R., Leech, R., Ogawa, T., Kawanabe, M. & Hyvarinen, A., 10 Jun 2020, In: PLoS ONE. 15, 6, p. e0232296 e0232296.
Research output: Contribution to journal › Article › peer-reviewOpen AccessFile7 Downloads (Pure)
Likelihood Inference for Large Scale Stochastic Blockmodels with Covariates based on a Divide-and-Conquer Parallelizable Algorithm with CommunicationRoy, S., Atchadé, Y. & Michailidis, G., 10 Jul 2019, In: Journal of Computational and Graphical Statistics. 28, 3, p. 609-619 12 p.
Research output: Contribution to journal › Article › peer-reviewOpen AccessFile1 Citation (Scopus)16 Downloads (Pure)
Roy, S., Atchade, Y. & Michailidis, G., 1 Sep 2017, In: Journal of the Royal Statistical Society: Series B - Statistical Methodology. 79, 4, p. 1187 - 1206 20 p.
Research output: Contribution to journal › Article › peer-reviewOpen AccessFile13 Citations (Scopus)46 Downloads (Pure)
Roy, S. & Bhattacharya, S., 1 Nov 2014, In: Statistical Methodology. 21, p. 35 - 48 14 p.
Research output: Contribution to journal › Article › peer-reviewOpen AccessFile8 Citations (Scopus)42 Downloads (Pure)