The man who wants to know it all, that’s me! I am hungry for information and for knowledge.
On a non-philosophical level, I am currently a post doctoral fellow jointly at the Department of Statistics, and the Department of Computer Science at Harvard University and a Visting Research Scientist at Carnegie Mellon University.
I am very fortunate to be working with Steve Fienberg at CMU, Edo Airlodi and Salil Vadhan at Harvard. Before this, I was a graduate student in the department of Statistics at Penn State University, where I was very fortunate to be advised by Sesa Slavković. For more on my background, please see this interview.I am lucky to be in the field of statistics as it lets me work across various disciplines.
Broadly, my research interests are in studying and developing methodology for latent variable models motivated by applications. Currently, I work on Differential Privacy, Causal Inference and Social network Models. I am also interested in developing fast computational inference procedures for Intractable likelihoods. I dabble in Algebraic Statistics and Machine learning.
Vishesh Karwa, Michael J. Pelsmajer, Sonja Petrović, Despina Stasi, Dane Wilburne. (2015) ``Statistical models for cores decomposition of an undirected random graph." ArxivId: 1410.7357.
Vishesh Karwa, Pavel N Krivitsky, Aleksandra Slavković. (2015) ``Sharing social network data - Differentially private estimation of exponential random graph models." ArxivId: 1511.02930.
Vishesh Karwa, Dan Kifer, Aleksandra Slavković. (2015). ``Private Posterior distributions from Variational approximations", NIPS 2015 Workshop on Learning and Privacy with Incomplete Data and Weak Supervision.
Vishesh Karwa, Aleksandra Slavković. (2015). ``Inference using noisy degrees - Differentially private synthetic graphs and $\beta$ models", The Annals of Statistics.
Vishesh Karwa, Sofya Raskhodnikova, Adam Smith, Grigory Yaroslavtsev. (2014). ``Private Analysis of Graph Structure'', ACM Transactions on Database Systems.
Vishesh Karwa, Aleksandra Slavković, Pavel Krivitsky. (2014). ``Differentially private Exponential Random graph models", Privacy in Statistical Databases.
Vishesh Karwa and Aleksandra Slavković, A. (2013). ``Conditional Inference given partial information in contingency tables using Markov Bases", Wiley Series on Computational Statistics. (Invited).
Minal Lalpuria, Vishesh Karwa, RC Anantheswaran, JD Floros. (2013). ``Modified agar diffusion bioassay for better quantification of Nisaplin®'', Journal of applied Microbiology.
Vishesh Karwa and Aleksandra Slavković, A. (2012) "Differentially private graphical degree sequences and synthetic graphs", Privacy in Statistical Databases
Vishesh Karwa, Aleksandra Slavković, and Eric T. Donnell. (2011). ``Causal Inference in Transportation Safety Studies: Comparison of Potential Outcomes and Causal Bayesian Networks'', The Annals of Applied Statistics
Vishesh Karwa, Sofya Raskhodnikova, Adam Smith, Grigory Yaroslavtsev. (2011). ``Private Analysis of Graph Structure'', Proceedings of Very Large DataBases.
Naomi Altman, Qing Wang, Vishesh Karwa, Aleksandra Slavković. (2010). ``Resolving Isoform Expression using Digital gene Expression Data''. Journal of Indian Society of Agricultural Statistics, Special Issue on Statistical Genomics. Vol. 64, Issue 1, pages 19-31
Vishesh Karwa, and Eric T. Donnell. (2010). ``Predicting Pavement Marking Retroreflectivity using Artificial Neural Networks'', The ASCE Journal of Transportation Engineering
Lekshmi Sasidharan, Vishesh Karwa, Eric T. Donnell. (2009). ``Use of Pavement Marking Degradation Models to Develop a Pavement Marking Management System'', Public Works Management and Policy, 14(2):148-173.
Eric T. Donnell, Vishesh Karwa, Sudhakar Sathyanarayanan. (2009). ``Analysis of Effects of Pavement Marking Retroreflectivity on Traffic Crash Frequency on Highways in North Carolina'', Transportation Research Record, 2103:50-60.
R4ti2 - An R package to compute Markov bases and construct markov chains on fibers. It has an interface to the algebraic software 4ti2 that computes the Markov bases.