Anand D. Sarwate
Assistant Professor
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: +18484458516
Email: anand.sarwate@rutgers.edu
Office Hours (Fall 2017):
Monday 1011 (CoRE 503)
Wednesday 1112 (CoRE 503)
Assistant Professor
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: +18484458516
Email: anand.sarwate@rutgers.edu
Office Hours (Fall 2017):
Monday 1011 (CoRE 503)
Wednesday 1112 (CoRE 503)
Recent news

New ArXiV papers:
Yihan Zhang, Shashank Vatedka, Sidharth Jaggi, Anand Sarwate, Quadratically Constrained Myopic Adversarial Channels.
Mohsen Ghassemi, Zahra Shakeri, Anand D. Sarwate, Waheed U. Bajwa, STARK: Structured Dictionary Learning Through Rankone Tensor Recovery.
Zahra Shakeri, Anand D. Sarwate, Waheed U. Bajwa, Identifiability of Kroneckerstructured Dictionaries for Tensor Data.  Kamalika Chaudhuri and I just gave a tutorial at NIPS 2017 on Differentially Private Machine Learning: Theory, Algorithms, and Applications. The tutorial site will have a full reference list soon.

New conference papers this semester!
GlobalSIP 2017: Hafiz Imtiaz and Anand D. Sarwate, Differentially Private Canonical Correlation Analysis, November 2017.
CAMSAP 2017: Mohsen Ghassemi, Zahra Shakeri, Anand D. Sarwate, Waheed U. Bajwa, STARK: Structured Dictionary Learning Through Rankone Tensor Recovery, December 2017.
CAMSAP 2017: Zahra Shakeri, Anand D. Sarwate, Waheed U. Bajwa, Identification of Kroneckerstructured Dictionaries: An Asymptotic Analysis, .

New journal paper in print:
A. Bijral, A.D. Sarwate, N. Srebro, Data Dependent Convergence For Consensus Stochastic Optimization, IEEE Transactions on Automatic Control 62 (9): pp. 44834498, September 2017.
 I'm teaching ECE 345 (Linear Systems and Signals) for Fall 2017. I always say Signals and Systems so I'm constantly switching them. Apparently Rutgers Students bypass this issue by calling the class LSS.
 Paper accepted to the IT Transactions: A. Lalitha, T. Javidi, A. Sarwate, Social Learning and Distributed Hypothesis Testing, preprint on ArXiV.
 I've officially been reappointed as an Assistant Professor in the ECE Department. Guess they haven't gotten rid of me yet!

New ArXiV paper (to appear in IEEE Cluster 2017):
Bangtian Liu, Chengyao Wen, Anand D. Sarwate, Maryam Mehri Dehnavi, A Unified Optimization Approach for Sparse Tensor Operations on GPUs, arXiv:1705.09905 [cs.MS], May 2017.
Some recent publications
Distributed learning and optimization
 A. Lalitha, T. Javidi, A. Sarwate, Social Learning and Distributed Hypothesis Testing, IEEE Transactions on Information Theory : to appear 2018. [BibTeX entry]
 A. Bijral, A.D. Sarwate, N. Srebro, Data Dependent Convergence For Consensus Stochastic Optimization, IEEE Transactions on Automatic Control 62(9): pp. 44834498, September 2017. [BibTeX entry]
 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. 1724, October 2015. [BibTeX entry]
 A.D. Sarwate, T. Javidi, Distributed Learning of Distributions via Social Sampling, IEEE Transactions on Automatic Control 60(1): pp. 3445, January 2015. [BibTeX entry] [Local/OA version]
Privacy
 H. Imtiaz, A.D. Sarwate, Differentially Private Distributed Principal Component Analysis, Proceedings of the 43rd IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2018), April 2018. [BibTeX entry]
 H. Imtiaz, A.D. Sarwate, Improved Algorithms for Differentially Private Orthogonal Tensor Decomposition, Proceedings of the 43rd IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2018), April 2018. [BibTeX entry]
 S. Xiong, A.D. Sarwate, N.B. Mandayam, Defending Against PacketSize SideChannel Attacks in IoT Networks, Proceedings of the 43rd IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2018), April 2018. [BibTeX entry]
 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, pp. 117128, October 2016. [BibTeX entry]
 C. Huang, L. Sankar, A.D. Sarwate, Designing Incentive Schemes For PrivacySensitive Users, Journal of Privacy and Confidentiality 7(1): pp. 99127, March 2016. [BibTeX entry]
 A.D. Sarwate, S.M. Plis, J.A. Turner, M.R. Arbabshirani, V.D. Calhoun, Sharing privacysensitive access to neuroimaging and genetics data: a review and preliminary validation, Frontiers in Neuroinformatics 8(35): 2014. [BibTeX entry] [Local/OA version]
 K. Chaudhuri, A.D. Sarwate, K. Sinha, A NearOptimal Algorithm for DifferentiallyPrivate Principal Components, Journal of Machine Learning Research 14: pp. 29052943, September 2013. [BibTeX entry] [Local/OA version]
Machine learning
 M. Ghassemi, N. Goela, A.D. Sarwate, Global Optimality in Inductive Matrix Completion, Proceedings of the 43rd IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2018), April 2018. [BibTeX entry]
 Z. Shakeri, A.D. Sarwate, W.U. Bajwa, Identifiability of Kroneckerstructured Dictionaries for Tensor Data, ArXiV report number arXiv:1712.03471 [stat.ML], December, 2017. [BibTeX entry]
 T. Hazan, F. Orabona, A.D. Sarwate, S. Maji, T. Jaakkola, High Dimensional Inference with Random Maximum APosteriori Perturbations, ArXiV report number arXiv:1602.03571 [cs.LG], February, 2016. [BibTeX entry]
 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]
 N.P. Santhanam, A.D. Sarwate, J.O. Woo, Redundancy of Exchangeable Estimators, Entropy 16(10): pp. 53395357, October 2014. [BibTeX entry] [Local/OA version]
 S. Sabato, A.D. Sarwate, N. Srebro, Auditing: Active Learning with OutcomeDependent Query Costs, ArXiV report number arXiv:1306.2347 [cs.LG], June, 2013. [BibTeX entry]
Information Theory
 Y. Zhang, S. Vatedka, S. Jaggi, A. Sarwate, Quadratically Constrained Myopic Adversarial Channels, ArXiV report number arXiv:1801.05951 [cs.IT], January, 2018. [BibTeX entry]
 A, ., , L, a, l, i, t, h, a, , a, n, d, , T, ., , J, a, v, i, d, i, , a, n, d, , A, ., , S, a, r, w, a, t, e, Social Learning and Distributed Hypothesis Testing, IEEE Transactions on Information Theory : to appear 2018. [BibTeX entry]
 Z. Shakeri, A.D. Sarwate, W.U. Bajwa, Identifiability of Kroneckerstructured Dictionaries for Tensor Data, IEEE Journal of Selected Topics in Signal Processing : to appear 2018. [BibTeX entry]
 Z. Shakeri, W.U. Bajwa, A.D. Sarwate, Minimax Lower Bounds on Dictionary Learning for Tensor Data, ArXiV report number arXiv:1608.02792 [cs.IT], August, 2016. [BibTeX entry]
 B.K. Dey, S. Jaggi, M. Langberg, A.D. Sarwate, The benefit of a 1bit jumpstart, and the necessity of stochastic encoding, in jamming channels, ArXiV report number arXiv:1602.02384 [cs.IT], February, 2016. [BibTeX entry]
Support
Some of my research is supported by grants
from generous agencies. Many thanks to them!
[NSF] SaTC1617849:
TWC: Small: PERMIT: PrivacyEnabled Resource Management for IoT Networks
(PI: Anand D. Sarwate, CoPI: 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), CoPIs: Anand D. Sarwate, David Cash)
[NSF] CCF1525276:
CIF: Small: Active data screening for efficient feature learning
(PI: Waheed Bajwa, CoPI: Anand D. Sarwate)
[NIH] 1R01DA04048701A1:
COINSTAC: Decentralized, Scalable Analysis of Loosely Coupled Data
(PI: Vince Calhoun (MRN)  subaward to Rutgers: Anand D. Sarwate (PI))
[NSF] CCF1453432
CAREER: Privacypreserving learning for distributed data
(PI: Anand D. Sarwate)
[NSF] CCF1218331/CCF1440033:
CIF: Small: Collaborative Research: Inference by social sampling
(PI: Anand Sarwate)