Anand D. Sarwate

I am an Associate 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

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.
Nov 27, 2023	I have been appointed as a Distinguished Lecturer for 2024-2025 by the IEEE Information Theory Society. I’m happy to visit to give a talk!
Nov 22, 2023	I received the Outstanding Engineering Professor Award from the Rutgers School of Engineering!
Sep 22, 2023	Some recent activity: Critical AI and Design Justice: An Interview with Sasha Costanza-Chock, to appear in Critical AI. This is the transcript of a panel interview with Sasha Costanza-Chock, author of Design Justice. Zhichao Wang, Andrew Engel, Anand Sarwate, Ioana Dumitriu, Tony Chiang, Spectral Evolution and Invariance in Linear-width Neural Networks, accepted to NeurIPS 2023.
Jun 20, 2023	A few new papers to appear: D. Martin et al. “Enhancing Collaborative Neuroimaging Research: Introducing COINSTAC Vaults for Federated Analysis and Reproducibility”, to Frontiers in Neuroinformatics. Z. Wang et al., “Spectral Evolution and Invariance in Linear-width Neural Networks”, to the ICML 2023 High-dimensional Learning Dynamics Workshop. D. Saha et al, “Federated, Fast, and Private Visualization of Decentralized Data”, to the ICML 2023 Workshop on Federated Learning and Analytics in Practice: Algorithms, Systems, Applications, and Opportunities.

selected publications

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

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

In The Twelfth International Conference on Learning Representations, May 2024

Bib
Low Separation Rank in Tensor Generalized Linear Models: an Asymptotic Analysis

Batoul Taki, Anand D. Sarwate, and Waheed U. Bajwa

In Proceedings of the 2024 Annual Conference on Information Science and Systems (CISS), Mar 2024

Bib
Spectral Evolution and Invariance in Linear-width Neural Networks

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

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

Bib
Federated, Fast, and Private Visualization of Decentralized Data

Debbrata Kumar Saha, Vince Calhoun, Soo Min Kwon, Anand Sarwate, Rekha Saha, and Sergey Plis

In Federated Learning and Analytics in Practice: Algorithms, Systems, Applications, and Opportunities (FL-ICML 2023), Jul 2023

Bib
Computationally Efficient Codes for Adversarial Binary-Erasure Channels

Sijie Li, Prasad Krishan, Sidharth Jaggi, Michael Langberg, and Anand D Sarwate

In Proceedings of the 2023 IEEE International Symposium on Information Theory (ISIT), Jun 2023

DOI Bib
Spectral evolution and invariance in linear-width neural networks

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

Nov 2022

DOI Bib
Federated Analysis in COINSTAC Reveals Functional Network Connectivity and Spectral Links to Smoking and Alcohol Consumption in Nearly 2,000 Adolescent Brains

Harshvardhan Gazula, Kelly Rootes-Murdy, Bharath Holla, Sunitha Basodi, Zuo Zhang, Eric Verner, Ross Kelly, Pratima Murthy, and 47 more authors

Neuroinformatics, Nov 2022

Abs DOI Bib

With the growth of decentralized/federated analysis approaches in neuroimaging, the opportunities to study brain disorders using data from multiple sites has grown multi-fold. One such initiative is the Neuromark, a fully automated spatially constrained independent component analysis (ICA) that is used to link brain network abnormalities among different datasets, studies, and disorders while leveraging subject-specific networks. In this study, we implement the neuromark pipeline in COINSTAC, an open-source neuroimaging framework for collaborative/decentralized analysis. Decentralized exploratory analysis of nearly 2000 resting-state functional magnetic resonance imaging datasets collected at different sites across two cohorts and co-located in different countries was performed to study the resting brain functional network connectivity changes in adolescents who smoke and consume alcohol. Results showed hypoconnectivity across the majority of networks including sensory, default mode, and subcortical domains, more for alcohol than smoking, and decreased low frequency power. These findings suggest that global reduced synchronization is associated with both tobacco and alcohol use. This proof-of-concept work demonstrates the utility and incentives associated with large-scale decentralized collaborations spanning multiple sites.
Quadratically Constrained Myopic Adversarial Channels

Yihan Zhang, Shashank Vatedka, Sidharth Jaggi, and Anand D. Sarwate

IEEE Transactions on Information Theory, Aug 2022

DOI Bib
The Capacity of Causal Adversarial Channels

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

In Proceedings of the 2022 IEEE International Symposium on Information Theory (ISIT), Jun 2022

DOI ArXiV Bib
Privacy Leakage in Discrete Time Updating Systems

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

In Proceedings of the 2022 IEEE International Symposium on Information Theory (ISIT), Jun 2022

DOI ArXiV Bib