Anand D. Sarwate

I am a Professor in the Department of Electrical and Computer Engineering at Rutgers, The State University of New Jersey. I also am a member of the graduate faculty in the Department of Computer Science and the Department of Statistics. I like to work on problems that involve probability, mathematical statistics, and optimization, with applications in information theory, communication, signal processing, and machine learning. I’m particularly interested in how these things intersect in the context of distributed/decentralized systems with constraints like privacy, bandwidth, latency, power, and so on.

This page is still somewhat under construction. I anticipate that will be the state for quite a while.

news

Nov 07, 2025	Two new papers accepted: Max Vargas, Reilly Cannon, Andrew Engel, Anand D. Sarwate, Tony Chiang, Understanding generative AI output with embedding models, Science Advances, in press. Anand D. Sarwate, Flavio Calmon, Oliver Kosut, Lalitha Sankar, An information theorist’s tour of differential privacy, BITS The Information Theory Magazine, in press.
Jul 01, 2025	Headed on an epic trip for the next 4 weeks. I’ll post the slides as well. 2025-07-24 Seminar at CUHK on adversarial models for communication. 2025-07-24 Invited talk at AICIT2025 on AI models as measurement instruments 2025-07-24 Seminar at Southwest Jiaotong University (Chengdu) on tensor signal processing. 2025-08-04 Seminar at University of Sydney on adversarial models for communication. 2025-08-07 Seminar at Macquarie University on information theory and DP. 026-08-14 Seminar at Melbourne University on adversarial models for communication. 2026-08-15 Seminar at Monash University on AI models as measurement instruments.
Jul 01, 2025	I’m a full Professor now! Woohoo!
May 23, 2025	A bunch of updates after not so many updates: The site has been updated with more content, including slides from some recent talks. I was awarded the Presidential Outstanding Faculty Scholar Award by Rutgers. This is given to faculty getting promoted to Professor (from Associate). However, I have not received official notification for the promotion so I’ll just assume the award is a good sign (?) Our monograph is finally done! Dey et al, Codes for Adversaries: Between Worst-Case and Average-Case Jamming, Foundations and Trends in Communications and Information Theory, 2024. This is is the culmination of 15+ years of research we’ve been doing on adversarial channel models! Preprints! Vargas et al., Understanding Generative AI Content with Embedding Models, under review. Tao et al., Privacy-Preserving Visualization of Brain Functional Connectivity, about to be submitted. Banerjee et al., Measuring model variability using robust non-parametric testing, revision under review. Journal and conference papers! Tao and Sarwate, Differentially Private Distribution Estimation Using Functional Approximation, ICASSP 2025. We look at CDF approximation using functional approximation. A journal version is in the works. Wu et al., Learning to Help in Multi-Class Settings, ICLR 2025. We study a variation on learning with abstention to design effective “helpers” for resource-constrained devices needing to do ML/AI stuff. Tao et al., Federated Privacy-Preserving Visualization: A Vision Paper, IEEE BigData 2024. We’re looking at where and when private visualization might be useful. Sathyavageeswaran et al., Timely Offloading in Mobile Edge Cloud Systems, ITW 2024. We use an MDP framework to analyze computational offloading policies. Dey, et al., Computationally Efficient Codes for Strongly Dobrushin-Stambler Nonsymmetrizable Oblivious AVCs, ISIT 2024. We develop polynomial time codes for classes of adversarial channels! A. D. Sarwate, Machine learning with differential privacy, a chapter in the Handbook of Sharing Confidential Data Differential Privacy, Secure Multiparty Computation, and Synthetic Data from CRC. A limited survey of “classical” ML under differential privacy, more aimed at potential practitioners. Rootes-Murdy et al., Cortical similarities in psychiatric and mood disorders identified in federated VBM analysis via COINSTAC, Patterns, 2024. A use-case for COINSTAC, the federated learning platform for neuroimaging analysis on which I have been collaborating for the last 10 years.
Jan 19, 2024	To appear at ICLR 2024 (spotlight): A. W. Engel, Z. Wang, N. Frank, I. Dumitriu, S. Choudhury, A. Sarwate, T. Chiang, Faithful and Efficient Explanations for Neural Networks via Neural Tangent Kernel Surrogate Models. To appear at ICASSP 2024: J. Hoyos Sanchez, B. Taki,, W. U. Bajwa, A. D. Sarwate, Federated Learning of Tensor Generalized Linear Models with Low Separation Rank. I’m teaching ECE 549 this semester, which was traditionally called Detection and Estimation Theory.

recent(-ish) publications

[Journal]

Anand D. Sarwate, Flavio P. Calmon, Oliver Kosut, and Lalitha Sankar,

An Information Theorist’s Tour of Differential Privacy

IEEE BITS the Information Theory Magazine to appear 2026

DOI Bib

        @article{SarwateCKS:26bits,
  author = {Sarwate, Anand D. and Calmon, Flavio P. and Kosut, Oliver and Sankar, Lalitha},
  doi = {10.1109/MBITS.2025.3625155},
  journal = {IEEE BITS the Information Theory Magazine},
  pages = {1--13},
  title = {An Information Theorist's Tour of Differential Privacy},
  year = {2026},
}

[Journal]

Max Vargas, Reilly Cannon, Andrew Engel, Anand D Sarwate, and Tony Chiang,

Understanding generative AI output with embedding models

Science Advances 11 : (48), Nov 2025

DOI Bib

        @article{VargasCESC:25embedding,
  author = {Vargas, Max and Cannon, Reilly and Engel, Andrew and Sarwate, Anand D and Chiang, Tony},
  day = {26},
  doi = {10.1126/sciadv.adx4082},
  journal = {Science Advances},
  month = nov,
  number = {48},
  title = {Understanding generative AI output with embedding models},
  year = {2025},
}

[Journal]

Sinjini Banerjee, Tim Marrinan, Reilly Cannon, Tony Chiang, and Anand D. Sarwate,

Measuring training variability from stochastic optimization using robust nonparametric testing

IEEE Journal of Selected Topics in Signal Processing 19 : (7), Oct 2025

DOI URL Bib

        @article{BanerjeeMCCS:25nonparam,
  author = {Banerjee, Sinjini and Marrinan, Tim and Cannon, Reilly and Chiang, Tony and Sarwate, Anand D.},
  doi = {10.1109/JSTSP.2025.3583140},
  journal = {IEEE Journal of Selected Topics in Signal Processing},
  month = oct,
  number = {7},
  pages = {1477--1492},
  title = {Measuring training variability from stochastic optimization using robust nonparametric testing},
  url = {https://doi.org/10.1109/JSTSP.2025.3583140},
  year = {2025},
}

[ArXiV]

Yu Wu, Shuo Wu, Ye Tao, Yansong Li, and Anand D. Sarwate,

Not only a helper, but also a teacher: Interactive LLM Cascade

ArXiv preprint arXiv:2509.22984 [cs.AI] Sep 2025

URL Bib

        @techreport{WuWTLS:25teacher,
  author = {Wu, Yu and Wu, Shuo and Tao, Ye and Li, Yansong and Sarwate, Anand D.},
  institution = {ArXiV},
  month = sep,
  number = {arXiv:2509.22984 [cs.AI]},
  title = {Not only a helper, but also a teacher: Interactive LLM Cascade},
  url = {https://arxiv.org/abs/2509.22984},
  year = {2025},
}

[ArXiV]

Bikash Kumar Dey, Sidharth Jaggi, Michael Langberg, Anand D. Sarwate, and Yihan Zhang,

Sliding Window Adversarial Channels

ArXiv preprint arXiv:2504.19773 [cs.IT] Apr 2025

URL Bib

        @techreport{DeyJLSZ:25slidingarxiv,
  author = {Dey, Bikash Kumar and Jaggi, Sidharth and Langberg, Michael and Sarwate, Anand D. and Zhang, Yihan},
  institution = {ArXiV},
  month = apr,
  number = {arXiv:2504.19773 [cs.IT]},
  title = {Sliding Window Adversarial Channels},
  url = {https://arxiv.org/abs/2504.19773},
  year = {2025},
}

[Conference]

Yu Wu, Yansong Li, Zeyu Dong, Nitya Sathyavageeswaran, and Anand D. Sarwate,

Learning to Help in Multi-Class Settings

In The Thirteenth International Conference on Learning Representations (ICLR 2025) Apr 2025

URL Bib

        @inproceedings{WuLDSS:25learning,
  author = {Wu, Yu and Li, Yansong and Dong, Zeyu and Sathyavageeswaran, Nitya and Sarwate, Anand D.},
  booktitle = {The Thirteenth International Conference on Learning Representations (ICLR 2025)},
  cvcategory = {archival},
  month = apr,
  title = {Learning to Help in Multi-Class Settings},
  url = {https://openreview.net/forum?id=NCgTbt2j1F},
  year = {2025},
}

[Conference]

Ye Tao, and Anand D. Sarwate,

Differentially Private Distribution Estimation Using Functional Approximation

In Proceedings of the 2025 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2025) Apr 2025

DOI Bib

        @inproceedings{TaoS:25cdf,
  author = {Tao, Ye and Sarwate, Anand D.},
  booktitle = {Proceedings of the 2025 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2025)},
  doi = {10.1109/ICASSP49660.2025.10890461},
  month = apr,
  title = {Differentially Private Distribution Estimation Using Functional Approximation},
  year = {2025},
}

[Conference]

Sunitha Basodi, Javier Romero, Sandeep Panta, Dylan Martin, Sergey Plis, Anand D. Sarwate, and Vince D. Calhoun,

Advanced machine learning in neuroimaging studies via federated learning

In 2024 IEEE International Conference on Big Data (BigData) Dec 2024

DOI Bib

        @inproceedings{BasodiRPMPSC:24fl,
  author = {Basodi, Sunitha and Romero, Javier and Panta, Sandeep and Martin, Dylan and Plis, Sergey and Sarwate, Anand D. and Calhoun, Vince D.},
  booktitle = {2024 IEEE International Conference on Big Data (BigData)},
  doi = {10.1109/BigData62323.2024.10825936},
  month = dec,
  pages = {8623--8624},
  title = {Advanced machine learning in neuroimaging studies via federated learning},
  year = {2024},
}

[Conference]
Ye Tao, Anand D. Sarwate, Sandeep Panta, Sergey Plis, and Vince D. Calhoun,

Federated Privacy-Preserving Visualization: A Vision Paper
In 2024 IEEE International Conference on Big Data (BigData) Dec 2024
.

Abs Bib

Privacy protection is important in visualization due to the risk of leaking personal sensitive information. In this paper, we study the problem of privacy-preserving visualizations using differential privacy, employing biomedical data from neuroimaging as a use case. We investigate several approaches based on perturbing correlation values and characterize their privacy cost and the impact of pre- and post-processing. To obtain a better privacy/visual utility tradeoff, we propose workflows for connectogram and seed-based connectivity visualizations, respectively. These workflows successfully generate visualizations similar to their non-private counterparts. Experiments show that qualitative assessments can be preserved while guaranteeing privacy. These results show that differential privacy is a promising method for protecting sensitive information in data visualization.Competing Interest StatementThe authors have declared no competing interest.
@inproceedings{TaoSPPC:24vision, author = {Tao, Ye and Sarwate, Anand D. and Panta, Sandeep and Plis, Sergey and Calhoun, Vince D.}, booktitle = {2024 IEEE International Conference on Big Data (BigData)}, month = dec, pages = {8035--8041}, title = {Federated Privacy-Preserving Visualization: A Vision Paper}, year = {2024}, bdsk-url-2 = {https://doi.org/10.1101/2024.10.11.617267} }

[Journal]

Bikash Kumar Dey, Sidharth Jaggi, Michael Langberg, Anand D. Sarwate, and Yihan Zhang,

Codes for Adversaries: Between Worst-Case and Average-Case Jamming

Foundations and Trends in Communications and Information Theory 21 : (3-4), Dec 2024

DOI URL Bib

        @article{DeyJLSZ:24monograph,
  author = {Dey, Bikash Kumar and Jaggi, Sidharth and Langberg, Michael and Sarwate, Anand D. and Zhang, Yihan},
  cvcategory = {books},
  doi = {10.1561/0100000112},
  issn = {1567-2190},
  journal = {Foundations and Trends in Communications and Information Theory},
  month = dec,
  number = {3-4},
  pages = {300-588},
  title = {Codes for Adversaries: Between Worst-Case and Average-Case Jamming},
  url = {http://dx.doi.org/10.1561/0100000112},
  year = {2024},
}

[Conference]

Nitya Sathyavageeswaran, Roy D Yates, Anand D Sarwate, and Narayan B. Mandayam,

Timely Offloading in Mobile Edge Cloud Systems

In Proceedings of the 2024 IEEE Information Theory Workshop Nov 2024

DOI Bib

        @inproceedings{Sathyavageeswaran:24itw,
  address = {Shenzhen, China},
  author = {Sathyavageeswaran, Nitya and Yates, Roy D and Sarwate, Anand D and Mandayam, Narayan B.},
  booktitle = {Proceedings of the 2024 IEEE Information Theory Workshop},
  doi = {10.1109/ITW61385.2024.10806971},
  month = nov,
  pages = {133--138},
  title = {Timely Offloading in Mobile Edge Cloud Systems},
  year = {2024},
}

[Book Chapter]

Anand D. Sarwate,

Machine learning with differential privacy

In Handbook of Sharing Confidential Data Differential Privacy, Secure Multiparty Computation, and Synthetic Data Oct 2024

DOI Bib

        @inbook{Sarwate:24crcbook,
  address = {Boca Raton, FL, USA},
  author = {Sarwate, Anand D.},
  booktitle = {Handbook of Sharing Confidential Data Differential Privacy, Secure Multiparty Computation, and Synthetic Data},
  chapter = {7},
  cvcategory = {books},
  doi = {10.1201/9781003185284-9},
  editor = {Drechsler, J\"{o}rg and Kifer, Daniel and Reiter, Jerome and Slavkovic, Aleksandra},
  month = oct,
  pages = {91--114},
  publisher = {CRC Press},
  series = {Chapman \& Hall/CRC Handbooks of Modern Statistical Methods},
  title = {Machine learning with differential privacy},
  year = {2024},
}

[Conference]

Ye Tao, Anand D. Sarwate, Sandeep Panta, Sergey Plis, and Vince D. Calhoun,

Privacy-Preserving Visualization of Brain Functional Network Connectivity

In 2024 IEEE International Symposium on Biomedical Imaging (ISBI) May 2024

DOI Bib

        @inproceedings{TaoSPPC:24fnc,
  author = {Tao, Ye and Sarwate, Anand D. and Panta, Sandeep and Plis, Sergey and Calhoun, Vince D.},
  booktitle = {2024 IEEE International Symposium on Biomedical Imaging (ISBI)},
  doi = {10.1109/ISBI56570.2024.10635222},
  month = may,
  pages = {1--5},
  title = {Privacy-Preserving Visualization of Brain Functional Network Connectivity},
  year = {2024},
}

[ArXiV]

Nitya Sathyavageeswaran, Roy D. Yates, Anand D. Sarwate, and Narayan Mandayam,

Timely Offloading in Mobile Edge Cloud Systems

ArXiv preprint arXiv:2405.07274 [eess.SY] May 2024

URL Bib

        @techreport{SathyavageeswaranYSM:24offloading,
  author = {Sathyavageeswaran, Nitya and Yates, Roy D. and Sarwate, Anand D. and Mandayam, Narayan},
  institution = {ArXiV},
  month = may,
  number = {arXiv:2405.07274 [eess.SY]},
  title = {Timely Offloading in Mobile Edge Cloud Systems},
  url = {https://arxiv.org/abs/2405.07274},
  year = {2024},
}

[Conference]

A. W. Engel, Z. Wang, N. Frank, I. Dumitriu, S. Choudhury, A. Sarwate, and T. Chiang,

Faithful and Efficient Explanations for Neural Networks via Neural Tangent Kernel Surrogate Models

In The Twelfth International Conference on Learning Representations May 2024

URL Bib

        @inproceedings{EngelWFDCSC:24explanations,
  address = {Vienna, Austria},
  author = {Engel, A. W. and Wang, Z. and Frank, N. and Dumitriu, I. and Choudhury, S. and Sarwate, A. and Chiang, T.},
  booktitle = {The Twelfth International Conference on Learning Representations},
  cvcategory = {archival},
  month = may,
  title = {Faithful and Efficient Explanations for Neural Networks via Neural Tangent Kernel Surrogate Models},
  url = {https://openreview.net/forum?id=yKksu38BpM},
  year = {2024},
}

[Conference]

Zhichao Wang, Andrew Engel, Anand Sarwate, Ioana Dumitriu, and Tony Chiang,

Spectral Evolution and Invariance in Linear-width Neural Networks

In Advances in Neural Information Processing Systems 36 (NeurIPS 2023) Dec 2023

URL Bib

        @incollection{WangESDC:23neurips,
  author = {Wang, Zhichao and Engel, Andrew and Sarwate, Anand and Dumitriu, Ioana and Chiang, Tony},
  booktitle = {Advances in Neural Information Processing Systems 36 (NeurIPS 2023)},
  cvcategory = {archival},
  month = dec,
  publisher = {Curran Associates, Inc.},
  title = {Spectral Evolution and Invariance in Linear-width Neural Networks},
  url = {https://openreview.net/forum?id=gpqBGyKeKH},
  year = {2023},
}