Anand D. Sarwate
Assistant Professor (from Jan. 2014)
Department of Electrical and Computer Engineering
Rutgers, The State University of New Jersey

Graduate Faculty, Dept. of Statistics
Associate Member, WINLAB
Affiliate Member, DIMACS

CoRE Building Rm. 517
Phone: +1-848-445-8516
Email: asarwate@ece.rutgers.edu
Recent news
  • Upcoming papers/talks this fall:

    A. Bijral, A.D. Sarwate, N. Srebro, Data-Dependent Bounds on Network Gradient Descent, Proceedings of the 54th Annual Allerton Conference on Communication, Control, and Computing (Allerton 2016).

    M. Ghassemi, A.D. Sarwate, R. Wright, Differentially Private Online Active Learning with Applications to Anomaly Detection, 9th ACM Workshop on Artificial Intelligence and Security (AISec 2016).

    L. Wei, A.D. Sarwate, J. Corander, A. Hero, and V. Tarokh, Analysis of a Privacy-preserving PCA Algorithm using Random Matrix Theory, 2016 IEEE Global Conference on Signal and Information Processing (GlobalSIP 2016).
  • New grant from the NSF Secure and Trustworthy Cyberspace (SaTC) program: PERMIT: Privacy-Enabled Resource Management for IoT Networks. Looking forward to working on this project!
  • I will be teaching ECE 436: Signal and Data Analysis, in Fall 2016. I really should have called the class "From Signal To Data Analysis" but too late now!
  • New papers:

    Z. Shakeri, W.U. Bajwa, and A.D. Sarwate, Minimax Lower Bounds on Dictionary Learning for Tensor Data, ArXiV 2016.

    S. Plis, A.D. Sarwate, D. Wood, C. Dieringer, D. Landis, C. Reed, S.R. Panta, J.A. Turner, J.M Shoemaker, K.W. Carter, P. Thompson, K. Hutchison, and V.D. Calhoun, COINSTAC: A Privacy Enabled Model and Prototype for Leveraging and Processing Decentralized Brain Imaging Data, Frontiers in Neuroscience 10 (365), 2016.

    Chong Huang, Lalitha Sankar, and Anand D. Sarwate, Incentive Schemes For Privacy-Sensitive Consumers, Journal of Privacy and Confidentiality 7 (1), 2016.

    Avleen S. Bijral, Anand D. Sarwate, and Nathan Srebro, On Data Dependence in Distributed Stochastic Optimization, ArXiV 2016.
  • Three papers appeared at ISIT 2016:

    Bikash Kumar Dey, Sidharth Jaggi, Michael Langberg, and Anand D. Sarwate, A bit of delay is sufficient and stochastic encoding is necessary to overcome online adversarial erasures.

    Kousha Kalantari, Lalitha Sankar, and Anand D. Sarwate, Optimal Differential Privacy Mechanisms under Hamming Distortion for Structured Source Classes.

    Zahra Shakeri, Waheed U. Bajwa, and Anand D. Sarwate, Minimax Lower Bounds for Kronecker-Structured Dictionary Learning.
Some recent publications
Distributed learning and optimization
  1. A. Bijral, A.D. Sarwate, N. Srebro, On Data Dependence in Distributed Stochastic Optimization, ArXiV report number arXiv:1603.04379 [math.OC], September, 2016. [BibTeX entry]
  2. L. Xie, S.M. Plis, A. Sarwate, Data Weighted Ensemble Learning for Privacy-Preserving Distributed Learning, Proceedings of the 2006 International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 2309--2313, March 2016. [BibTeX entry]
  3. M. Ghassemi, A.D. Sarwate, Distributed Proportional Stochastic Coordinate Descent with Social Sampling, Proceedings of the 53rd Annual Allerton Conference on Communication, Control, and Computing, pp. 17--24, October 2015. [BibTeX entry]
  4. A.D. Sarwate, T. Javidi, Distributed Learning of Distributions via Social Sampling, IEEE Transactions on Automatic Control 60(1): pp. 34--45, January 2015. [BibTeX entry] [Local/OA version]
Privacy
  1. M. Ghassemi, A.D. Sarwate, R. Wright, Differentially Private Online Active Learning with Applications to Anomaly Detection, Proceedings of the 9th ACM Workshop on Artificial Intelligence and Security, October 2016. [BibTeX entry]
  2. C. Huang, L. Sankar, A.D. Sarwate, Designing Incentive Schemes For Privacy-Sensitive Users, Journal of Privacy and Confidentiality 7(1): March 2016. [BibTeX entry]
  3. H. Imtiaz, A.D. Sarwate, Symmetric Matrix Perturbation for Differentially-Private Principal Component Analysis, Proceedings of the 2016 International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 2339--2343, March 2016. [BibTeX entry]
  4. A.D. Sarwate, S.M. Plis, J.A. Turner, M.R. Arbabshirani, V.D. Calhoun, Sharing privacy-sensitive access to neuroimaging and genetics data: a review and preliminary validation, Frontiers in Neuroinformatics 8(35): 2014. [BibTeX entry] [Local/OA version]
  5. K. Chaudhuri, A.D. Sarwate, K. Sinha, A Near-Optimal Algorithm for Differentially-Private Principal Components, Journal of Machine Learning Research 14: pp. 2905--2943, September 2013. [BibTeX entry] [Local/OA version]
Machine learning
  1. T. Hazan, F. Orabona, A.D. Sarwate, S. Maji, T. Jaakkola, High Dimensional Inference with Random Maximum A-Posteriori Perturbations, ArXiV report number arXiv:1602.03571 [cs.LG], February, 2016. [BibTeX entry]
  2. S. Song, K. Chaudhuri, A.D. Sarwate, Learning from Data with Heterogeneous Noise using SGD, ArXiV report number arXiv:1412.5617 [cs.LG], December, 2014. [BibTeX entry]
  3. N.P. Santhanam, A.D. Sarwate, J.O. Woo, Redundancy of Exchangeable Estimators, Entropy 16(10): pp. 5339--5357, October 2014. [BibTeX entry] [Local/OA version]
  4. S. Sabato, A.D. Sarwate, N. Srebro, Auditing: Active Learning with Outcome-Dependent Query Costs, ArXiV report number arXiv:1306.2347 [cs.LG], June, 2013. [BibTeX entry]
Information Theory
  1. Z. Shakeri, W.U. Bajwa, A.D. Sarwate, Minimax Lower Bounds for Kronecker-Structured Dictionary Learning, Proceedings of the 2016 IEEE International Symposium on Information Theory, pp. 1148--1152, July 10--15 2016. [BibTeX entry]
  2. A. Lalitha, T. Javidi, A. Sarwate, Social Learning and Distributed Hypothesis Testing, ArXiV report number arXiv:1410.4307v5 [math.ST], May, 2016. [BibTeX entry]
  3. B.K. Dey, S. Jaggi, M. Langberg, A.D. Sarwate, The benefit of a 1-bit jump-start, and the necessity of stochastic encoding, in jamming channels, ArXiV report number arXiv:1602.02384 [cs.IT], February, 2016. [BibTeX entry]
  4. A.D. Sarwate, A.G. Dimakis, The Impact of Mobility on Gossip Algorithms, IEEE Transactions on Information Theory 58(3): pp. 1731--1742, March 2012. [BibTeX entry] [Local/OA version]
  5. A.D. Sarwate, M. Gastpar, List-Decoding for the Arbitrarily Varying Channel Under State Constraints, IEEE Transactions on Information Theory 58(3): pp. 1372--1384, March 2012. [BibTeX entry] [Local/OA version]
Support
Some of my research is supported by grants from generous agencies. Many thanks to them!
[NSF] SaTC-1617849: TWC: Small: PERMIT: Privacy-Enabled Resource Management for IoT Networks (PI: Anand D. Sarwate, Co-PI: Narayan B. Mandayam)
[Verisign] gift through DIMACS Center to work on applied and theoretical privacy (PIs: Rebecca Wright, Anand D. Sarwate)
[DHS] through CCICADA Center: DPAD: Differentially Private Anomaly Detection (PIs: Rebecca Wright, Anand D. Sarwate)
[DARPA] Brandeis, subcontract with Galois, Inc.: Jana: Ensuring Secure, Private and Flexible Data Access (PI: David Archer (Galois) -- subaward to Rutgers: Rebecca Wright (PI), Co-PIs: Anand D. Sarwate, David Cash)
[NSF] CCF-1525276: CIF: Small: Active data screening for efficient feature learning (PI: Waheed Bajwa, Co-PI: Anand D. Sarwate)
[NIH] 1R01DA040487-01A1: COINSTAC: Decentralized, Scalable Analysis of Loosely Coupled Data (PI: Vince Calhoun (MRN) -- subaward to Rutgers: Anand D. Sarwate (PI))
[NSF] CCF-1453432 CAREER: Privacy-preserving learning for distributed data (PI: Anand D. Sarwate)
[NSF] CCF-1218331/CCF-1440033: CIF: Small: Collaborative Research: Inference by social sampling (PI: Anand Sarwate)