Research
I currently work in the PrDB project, which aims at developing a probabilistic database system that can manage large scale uncertain databases with correlations. Earlier, I worked in the MauveDB project, which aims at integrating probabilistic and statistical models in relational database systems so that such models can be effectively and efficiently applied to data streams.
Publications(1) Online Filtering, Smoothing and Probabilistic Modeling of Streaming Data. Bhargav Kanagal, Amol Deshpande. ICDE 2008. Link to technical report (CS-TR-4867) [link], conference paper [pdf], presentation [pptx]
(2) Efficient Query Evaluation over Temporally Correlated Probabilistic Streams. Bhargav Kanagal, Amol Deshpande. ICDE 2009. (Short paper). Link to technical report (CS-TR-4916) [pdf], conference paper [pdf], poster [pdf]
(3) Indexing Correlated Probabilistic databases. Bhargav Kanagal, Amol Deshpande. SIGMOD 2009. conference paper [pdf], presentation [pptx]
(4) Lineage Processing over Correlated Probabilistic databases. Bhargav Kanagal, Amol Deshpande. SIGMOD 2010. conference paper [pdf], presentation [pptx]
(5) Rank Selection in Low-rank Matrix Approximations: A Study of Cross-Validation for NMFs. Bhargav Kanagal, Vikas Sindhwani. To appear in Workshop: Low-rank Methods for Large-scale Machine Learning, NIPS 2010. Preprint [pdf]
(6) Sensitivity Analysis and Explanations for Robust Query Evaluation in Probabilistic Databases. Bhargav Kanagal, Jian Li, Amol Deshpande. To appear in SIGMOD 2011. conference paper[pdf]
Earlier Work
(7) Defining and Enforcing C's Module System. Saurabh Srivastava, Michael Hicks, Jeffrey S Foster, and Bhargav Kanagal. University of Maryland Technical Report CS-TR-4816, University of Maryland, July 2006.