publications | Anand D. Sarwate

Preprints

Understanding Generative AI Content with Embedding Models

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

Aug 2024

DOI Bib
Measuring model variability using robust non-parametric testing

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

Jun 2024

DOI Bib
Timely Offloading in Mobile Edge Cloud Systems

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

May 2024

Bib
Minibatching Offers Improved Generalization Performance for Second Order Optimizers

Eric Silk, Swarnita Chakraborty, Nairanjana Dasgupta, Anand D. Sarwate, Andrew Lumsdaine, and Tony Chiang

May 2023

DOI Bib
TorchNTK: A Library for Calculation of Neural Tangent Kernels of PyTorch Models

Andrew Engel, Zhichao Wang, Anand D. Sarwate, Sutanay Choudhury, and Tony Chiang

May 2022

Bib
Optimal Rates for Learning Hidden Tree Structures

Konstantinos E. Nikolakakis, Dionysios S. Kalogerias, and Anand D. Sarwate

Mar 2021

Bib

Monographs and Book Chapters

Machine learning with differential privacy

Anand D. Sarwate

Oct 2024

Bib
Sample Complexity Bounds for Dictionary Learning from Vector- and Tensor-valued Data

Zahra Shakeri, Anand D. Sarwate, and Waheed U. Bajwa

Mar 2021

DOI Bib

Journal Papers

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

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

Foundations and Trends\textregistered in Communications and Information Theory, Dec 2024

DOI Bib
Cortical similarities in psychiatric and mood disorders identified in federated VBM analysis via COINSTAC

Kelly Rootes-Murdy, Sandeep Panta, Ross Kelly, Javier Romero, Yann Quidé, Murray J. Cairns, Carmel Loughland, Vaughan J. Carr, and 41 more authors

Patterns, May 2024

Abs DOI Bib Local

Summary Structural neuroimaging studies have identified a combination of shared and disorder-specific patterns of gray matter (GM) deficits across psychiatric disorders. Pooling large data allows for examination of a possible common neuroanatomical basis that may identify a certain vulnerability for mental illness. Large-scale collaborative research is already facilitated by data repositories, institutionally supported databases, and data archives. However, these data-sharing methodologies can suffer from significant barriers. Federated approaches augment these approaches by enabling access or more sophisticated, shareable and scaled-up analyses of large-scale data. We examined GM alterations using Collaborative Informatics and Neuroimaging Suite Toolkit for Anonymous Computation, an open-source, decentralized analysis application. Through federated analysis of eight sites, we identified significant overlap in the GM patterns (n = 4,102) of individuals with schizophrenia, major depressive disorder, and autism spectrum disorder. These results show cortical and subcortical regions that may indicate a shared vulnerability to psychiatric disorders.
Critical AI and Design Justice: An Interview with Sasha Costanza-Chock

Sasha Costanza-Chock, Kristin Rose (editor), Kate Henne, Sabelo Mhlambi, and Anand Sarwate

Critical AI, Oct 2023

DOI Bib
Structured Low-Rank Tensor Models for Logistic Regression

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

Transactions on Machine Learning Research, Aug 2023

Bib
Enhancing collaborative neuroimaging research: introducing COINSTAC Vaults for federated analysis and reproducibility

Dylan Martin, Sunitha Basodi, Sandeep Panta, Kelly Rootes-Murdy, Paul Prae, Anand D. Sarwate, Ross Kelly, Javier Romero, and 8 more authors

Frontiers in Neuroinformatics, Jun 2023

Abs DOI Bib

Collaborative neuroimaging research is often hindered by technological, policy, administrative, and methodological barriers, despite the abundance of available data. COINSTAC (The Collaborative Informatics and Neuroimaging Suite Toolkit for Anonymous Computation) is a platform that successfully tackles these challenges through federated analysis, allowing researchers to analyze datasets without publicly sharing their data. This paper presents a significant enhancement to the COINSTAC platform: COINSTAC Vaults (CVs). CVs are designed to further reduce barriers by hosting standardized, persistent, and highly-available datasets, while seamlessly integrating with COINSTAC’s federated analysis capabilities. CVs offer a user-friendly interface for self-service analysis, streamlining collaboration, and eliminating the need for manual coordination with data owners. Importantly, CVs can also be used in conjunction with open data as well, by simply creating a CV hosting the open data one would like to include in the analysis, thus filling an important gap in the data sharing ecosystem. We demonstrate the impact of CVs through several functional and structural neuroimaging studies utilizing federated analysis showcasing their potential to improve the reproducibility of research and increase sample sizes in neuroimaging studies.
Approximating Functions with Approximate Privacy for Applications in Signal Estimation and Learning

Naima Tasnim, Jafar Mohammadi, Anand D Sarwate, and Hafiz Imtiaz

Entropy, May 2023

DOI Bib
Differential Fairness: An Intersectional Framework for Fair AI

Rashidul Islam, Kamrun Naher Keya, Shimei Pan, Anand D. Sarwate, and James R. Foulds

Entropy, Apr 2023

Abs DOI Bib

We propose definitions of fairness in machine learning and artificial intelligence systems that are informed by the framework of intersectionality, a critical lens from the legal, social science, and humanities literature which analyzes how interlocking systems of power and oppression affect individuals along overlapping dimensions including gender, race, sexual orientation, class, and disability. We show that our criteria behave sensibly for any subset of the set of protected attributes, and we prove economic, privacy, and generalization guarantees. Our theoretical results show that our criteria meaningfully operationalize AI fairness in terms of real-world harms, making the measurements interpretable in a manner analogous to differential privacy. We provide a simple learning algorithm using deterministic gradient methods, which respects our intersectional fairness criteria. The measurement of fairness becomes statistically challenging in the minibatch setting due to data sparsity, which increases rapidly in the number of protected attributes and in the values per protected attribute. To address this, we further develop a practical learning algorithm using stochastic gradient methods which incorporates stochastic estimation of the intersectional fairness criteria on minibatches to scale up to big data. Case studies on census data, the COMPAS criminal recidivism dataset, the HHP hospitalization data, and a loan application dataset from HMDA demonstrate the utility of our methods.
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
Network Traffic Shaping for Enhancing Privacy in IoT Systems

Sijie Xiong, Anand D Sarwate, and Narayan B Mandayam

IEEE/ACM Transactions on Networking, Jun 2022

DOI Bib
Decentralized Brain Age Estimation Using MRI Data

Sunitha Basodi, Rajikha Raja, Bhaskar Ray, Harshvardhan Gazula, Anand D. Sarwate, Sergey Plis, Jingyu Liu, Eric Verner, and 1 more author

Neuroinformatics, Apr 2022

Abs DOI Bib

Recent studies have demonstrated that neuroimaging data can be used to estimate biological brain age, as it captures information about the neuroanatomical and functional changes the brain undergoes during development and the aging process. However, researchers often have limited access to neuroimaging data because of its challenging and expensive acquisition process, thereby limiting the effectiveness of the predictive model. Decentralized models provide a way to build more accurate and generalizable prediction models, bypassing the traditional data-sharing methodology. In this work, we propose a decentralized method for biological brain age estimation using support vector regression models and evaluate it on three different feature sets, including both volumetric and voxelwise structural MRI data as well as resting functional MRI data. The results demonstrate that our decentralized brain age regression models can achieve similar performance compared to the models trained with all the data in one location.
Federated Analysis of Neuroimaging Data: A Review of the Field

Kelly Rootes-Murdy, Harshvardhan Gazula, Eric Verner, Ross Kelly, Thomas DeRamus, Sergey Plis, Anand Sarwate, Jessica Turner, and 1 more author

Neuroinformatics, Apr 2022

Abs DOI Bib

The field of neuroimaging has embraced sharing data to collaboratively advance our understanding of the brain. However, data sharing, especially across sites with large amounts of protected health information (PHI), can be cumbersome and time intensive. Recently, there has been a greater push towards collaborative frameworks that enable large-scale federated analysis of neuroimaging data without the data having to leave its original location. However, there still remains a need for a standardized federated approach that not only allows for data sharing adhering to the FAIR (Findability, Accessibility, Interoperability, Reusability) data principles, but also streamlines analyses and communication while maintaining subject privacy. In this paper, we review a non-exhaustive list of neuroimaging analytic tools and frameworks currently in use. We then provide an update on our federated neuroimaging analysis software system, the Collaborative Informatics and Neuroimaging Suite Toolkit for Anonymous Computation (COINSTAC). In the end, we share insights on future research directions for federated analysis of neuroimaging data.
Privacy-preserving quality control of neuroimaging datasets in federated environments

Debbrata K Saha, Vince D Calhoun, Yuhui Du, Zening Fu, Soo Min Kwon, Anand D Sarwate, Sandeep R Panta, and Sergey M Plis

Human Brain Mapping, Mar 2022

DOI Bib
A Correlated Noise-Assisted Decentralized Differentially Private Estimation Protocol, and its Application to fMRI Source Separation

Hafiz Imtiaz, Jafar Mohammadi, Rogers Silva, Bradley Baker, Sergey M. Plis, Anand D. Sarwate, and Vince D. Calhoun

IEEE Transactions on Signal Processing, Nov 2021

DOI Bib
Learning Predictors from Multidimensional Data with Tensor Factorizations

Soo Min Kwon, and Anand D Sarwate

Aresty Rutgers Undergraduate Research Journal, Oct 2021

DOI Bib
Coordination Through Shared Randomness

Gowtham R. Kurri, Vinod M. Prabhakaran, and Anand D. Sarwate

IEEE Transactions on Information Theory, Aug 2021

DOI Bib
Quantile Multi-Armed Bandits: Optimal Best-Arm Identification and a Differentially Private Scheme

Konstantinos E Nikolakakis, Dionysios S Kalogerias, Anand D Sarwate, and Or Sheffet

IEEE Journal on Selected Areas in Information Theory, Jun 2021

DOI Bib
Predictive Learning on Hidden Tree-Structured Ising Models

Konstantinos E Nikolakakis, Dionysios S Kalogerias, and Anand D Sarwate

Journal of Machine Learning Research, Apr 2021

Bib
Decentralized Multisite VBM Analysis During Adolescence Shows Structural Changes Linked to Age, Body Mass Index, and Smoking: a COINSTAC Analysis

Harshvardhan Gazula, Bharath Holla, Zuo Zhang, Jiayuan Xu, Eric Verner, Ross Kelly, Sanjeev Jain, Rose Dawn Bharath, and 14 more authors

Neuroinformatics, Jan 2021

DOI Bib
COINSTAC: Collaborative Informatics and Neuroimaging Suite Toolkit for Anonymous Computation

Harshvardhan Gazula, Ross Kelly, Javier Romero, Eric Verner, Bradley T. Baker, Rogers F. Silva, Hafiz Imtiaz, Debbrata Kumar Saha, and 5 more authors

Journal of Open Source Software, Oct 2020

DOI Bib
Understanding Privacy-Utility Tradeoffs Using Differentially Private Online Active Learning

Daniel M. Bittner, Alejandro E. Brito, Mohsen Ghassemi, Shantanu Rane, Anand D. Sarwate, and Rebecca N. Wright

Journal of Privacy and Confidentiality, Jun 2020

DOI Bib
Learning Mixtures of Separable Dictionaries for Tensor Data: Analysis and Algorithms

Mohsen Ghassemi, Zahra Shakeri, Anand D. Sarwate, and Waheed U. Bajwa

IEEE Transactions on Signal Processing, Jan 2020

DOI Bib
High Dimensional Inference with Random Maximum A-Posteriori Perturbations

Tamir Hazan, Francesco Orabona, Anand D. Sarwate, Subhransu Maji, and Tommi Jaakkola

IEEE Transactions on Information Theory, Oct 2019

DOI Bib Local
Decentralized Temporal Independent Component Analysis: Leveraging fMRI Data in Collaborative Settings

Bradley Baker, Anees Abrol, Rogers F. Silva, Eswar Damaraju, Anand D Sarwate, Vince D Calhoun, and Sergey M Plis

NeuroImage, Feb 2019

DOI Bib Local
Distributed Differentially-Private Algorithms for Matrix and Tensor Factorization

Hafiz Imtiaz, and Anand D. Sarwate

IEEE Journal of Selected Topics in Signal Processing, Dec 2018

DOI Bib Local
Robust Privacy-Utility Tradeoffs under Differential Privacy and Hamming Distortion

Kousha Kalantari, Lalitha Sankar, and Anand D. Sarwate

IEEE Transactions on Information Forensics and Security, Nov 2018

DOI Bib Local
Identifiability of Kronecker-Structured Dictionaries for Tensor Data

Zahra Shakeri, Anand D Sarwate, and Waheed U. Bajwa

IEEE Journal of Selected Topics in Signal Processing, Oct 2018

DOI Bib Local
Social Learning and Distributed Hypothesis Testing

Anusha Lalitha, Tara Javidi, and Anand D. Sarwate

IEEE Transactions on Information Theory, Sep 2018

DOI Bib Local
Minimax Lower Bounds on Dictionary Learning for Tensor Data

Zahra Shakeri, Waheed U. Bajwa, and Anand D. Sarwate

IEEE Transactions on Information Theory, Apr 2018

DOI Bib Local
Data Dependent Convergence For Consensus Stochastic Optimization

Avleen Bijral, Anand D. Sarwate, and Nathan Srebro

IEEE Transactions on Automatic Control, Sep 2017

DOI Bib Local
COINSTAC: Decentralizing the future of brain imaging analysis

J. Ming, E. Verner, A. Sarwate, R. Kelly, C. Reed, T. Kahleck, R. Silva, S. Panta, and 3 more authors

F1000Research, Aug 2017

DOI Bib Local
Privacy, security, and the public health researcher in the era of electronic health record research

Neal D. Goldstein, and Anand D. Sarwate

Online Journal of Public Health Informatics, Dec 2016

DOI Bib Local
COINSTAC: A Privacy Enabled Model and Prototype for Leveraging and Processing Decentralized Brain Imaging Data

Sergey Plis, Anand D. Sarwate, Dylan Wood, Christopher Dieringer, Drew Landis, Cory Reed, Sandeep R. Panta, Jessica A. Turner, and 5 more authors

Frontiers in Neuroscience, Aug 2016

DOI Bib Local
Designing Incentive Schemes For Privacy-Sensitive Users

Chong Huang, Lalitha Sankar, and Anand D. Sarwate

Journal of Privacy and Confidentiality, Mar 2016

Bib Local
Distributed Learning of Distributions via Social Sampling

Anand D. Sarwate, and Tara Javidi

IEEE Transactions on Automatic Control, Jan 2015

DOI Bib Local
Redundancy of Exchangeable Estimators

Narayana P. Santhanam, Anand D. Sarwate, and Jae Oh Woo

Entropy, Oct 2014

DOI Bib Local
Sharing privacy-sensitive access to neuroimaging and genetics data: a review and preliminary validation

Anand D. Sarwate, Sergey M. Plis, Jessica A. Turner, Mohammad R. Arbabshirani, and Vince D. Calhoun

Frontiers in Neuroinformatics, Apr 2014

DOI Bib Local
Signal processing and machine learning with differential privacy: theory, algorithms, and challenges

Anand D. Sarwate, and Kamalika Chaudhuri

IEEE Signal Processing Magazine, Sep 2013

DOI Bib Local
A Near-Optimal Algorithm for Differentially-Private Principal Components

Kamalika Chaudhuri, Anand D. Sarwate, and Kaushik Sinha

Journal of Machine Learning Research, Sep 2013

Bib Local
Privacy Technology to Share Data for Comparative Effectiveness Research : a systematic review

Xiaoqian Jiang, Anand D. Sarwate, and Lucila Ohno-Machado

Medical Care, Aug 2013

DOI Bib Local
Upper Bounds on the Capacity of Binary Channels with Causal Adversaries

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

IEEE Transactions on Information Theory, Jun 2013

DOI Bib Local
Risk-Limiting Audits and the Margin of Victory in Nonplurality Elections

Anand D. Sarwate, Stephen Checkoway, and Hovav Shacham

Statistics, Politics and Policy, Dec 2012

DOI Bib Local
Protecting Count Queries in Study Design

Staal A. Vinterbo, Anand D. Sarwate, and Aziz Boxwala

Journal of the American Medical Informatics Association, Sep 2012

DOI Bib Local
The Impact of Mobility on Gossip Algorithms

Anand D. Sarwate, and Alexandros G. Dimakis

IEEE Transactions on Information Theory, Mar 2012

DOI Bib Local
List-Decoding for the Arbitrarily Varying Channel Under State Constraints

Anand D. Sarwate, and Michael Gastpar

IEEE Transactions on Information Theory, Mar 2012

DOI Bib Local
Differentially private empirical risk minimization

Kamalika Chaudhuri, Claire Monteleoni, and Anand D. Sarwate

Journal of Machine Learning Research, Mar 2011

Bib Local
A little feedback can simplify sensor network cooperation

Anand D. Sarwate, and Michael Gastpar

IEEE Journal of Selected Areas in Communication, Sep 2010

DOI Bib Local
Rateless codes for AVC models

Anand D. Sarwate, and Michael Gastpar

IEEE Transactions on Information Theory, Jul 2010

DOI Bib Local
Zero-rate feedback can achieve the empirical capacity

Krishnan Eswaran, Anand D. Sarwate, Anant Sahai, and Michael Gastpar

IEEE Transactions on Information Theory, Jan 2010

DOI Bib Local
Broadcast Gossip Algorithms for Consensus

Tuncer Can Aysal, Mehmet Ercan Yildiz, Anand D. Sarwate, and Anna Scaglione

IEEE Transactions on Signal Processing, Jul 2009

DOI Bib Local
Geographic Gossip: Efficient Averaging for Sensor Networks

Alexandros G. Dimakis, Anand D. Sarwate, and Martin J. Wainwright

IEEE Transactions on Signal Processing, Mar 2008

DOI Bib Local
Exact emulation of a priority queue with a switch and delay lines

Anand D. Sarwate, and Venkat Anantharam

Queuing Systems : Theory and Applications, Jul 2006

DOI Bib Local
Longest Increasing Subsequences and Random Matrices

Anand Sarwate

MIT Undergraduate Journal of Mathematics, Jul 2002

Bib Local

Conference Papers

Learning to Help in Multi-Class Settings

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

In The Thirteenth International Conference on Learning Representations, Apr 2025

Bib
Differentially Private Distribution Estimation Using Functional Approximation

Ye Tao, and Anand D. Sarwate

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

Bib
Federated Analysis of Neuroimaging Data Using COINSTAC

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

In 2025 IEEE International Symposium on Biomedical Imaging (ISBI), Apr 2025

Bib
Advanced machine learning in neuroimaging studies via federated learning

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

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

DOI Bib
Federated Privacy-Preserving Visualization: A Vision Paper

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

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.
Timely Offloading in Mobile Edge Cloud Systems

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

In Proceedings of the 2024 IEEE Information Theory Workshop, Nov 2024

DOI Bib
Computationally Efficient Codes for Strongly Dobrushin-Stambler Nonsymmetrizable Oblivious AVCs

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

In Proceedings of the 2024 IEEE International Symposium on Information Theory (ISIT), Jul 2024

Bib
Privacy-Preserving Visualization of Brain Functional Network Connectivity

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

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

DOI Bib
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
Federated Learning of Tensor Generalized Linear Models with Low Separation Rank

Jose Hoyos Sanchez, Batoul Taki, Waheed Bajwa, and Anand Sarwate

In Proceedings of the 2024 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2024), Apr 2024

DOI 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
Spectral Evolution and Invariance in Linear-width Neural Networks

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

In Workshop on High-dimensional Learning Dynamics (HiLD-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
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
Low-Rank Phase Retrieval with Structured Tensor Models

Soo Min Kwon, Xin Li, and Anand D. Sarwate

In Proceedings of the 47th IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2022), May 2022

DOI ArXiV Bib
Privid: Practical, Privacy-Preserving Video Analytics Queries

Frank Cangialosi, Neil Agarwal, Venkat Arun, Junchen Jiang, Srinivas Narayana, Anand Sarwate, and Ravi Netravali

In Proceedings of the 19th USENIX Symposium on Networked Systems Design and Implementation (NSDI ’22), Apr 2022

Bib
Privacy-Preserving Visualization of Functional Network Connectivity

Ye Tao, Anis Chihoub, Anand D Sarwate, Sandeep Panta, and Vince Calhoun

In International Conference of the IEEE Engineering in Medicine and Biology Society, Apr 2022

Bib
A Minimax Lower Bound for Low-Rank Matrix-Variate Logistic Regression

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

In 2021 Asilomar Conference on Signals, Systems, and Computers, Nov 2021

DOI ArXiV Bib
Influencers and the Giant Component: the Fundamental Hardness in Privacy Protection for Socially Contagious Attributes

Aria Rezaie, Jie Gao, and Anand D. Sarwate

In SIAM International Conference on Data Mining, Apr 2021

DOI Bib
Symmetrizability for Myopic AVCs

Amitalok J. Budkuley, Bikash Kumar Dey, Sidharth Jaggi, Michael Langberg, Anand D. Sarwate, and Carol Wang

In Proceedings of the 2020 IEEE International Symposium on Information Theory (ISIT), Jun 2020

DOI Bib
The Interplay of Causality and Myopia in Adversarial Channel Models

Bikash Kumar Dey, Sidharth Jaggi, Michael Langberg, Anand D. Sarwate, and Carol Wang

In Proceedings of the 2019 IEEE International Symposium on Information Theory (ISIT), Jul 2019

DOI Bib
Sample Complexity Bounds for Low-Separation-Rank Dictionary Learning

Mohsen Ghassemi, Zahra Shakeri, Waheed U. Bajwa, and Anand D. Sarwate

In Proceedings of the 2019 IEEE International Symposium on Information Theory (ISIT), Jul 2019

DOI Bib
Distributed Differentially Private Canonical Correlation Analysis

Hafiz Imtiaz, and Anand D. Sarwate

In Proceedings of the 44th IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), May 2019

DOI Bib
Learning Tree Structures from Noisy Data

Konstantinos Nikolakakis, Dionysios Kalogerias, and Anand D. Sarwate

In Proceedings of the Twenty-Second International Conference on Artificial Intelligence and Statistics (AISTATS), Apr 2019

Bib Local
Quadratically Constrained Myopic Adversarial Channels

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

In Proceedings of the 2018 IEEE International Symposium on Information Theory (ISIT), Jun 2018

DOI Bib
Quadratically Constrained Channels with Causal Adversaries

Tongxin Li, Bikash Kumar Dey, Sidharth Jaggi, Michael Langberg, and Anand D. Sarwate

In Proceedings of the 2018 IEEE International Symposium on Information Theory (ISIT), Jun 2018

DOI ArXiV Bib
Coordination Using Individually Shared Randomness

Gowtham R. Kurri, Vinod M. Prabhakaran, and Anand D. Sarwate

In Proceedings of the 2018 IEEE International Symposium on Information Theory (ISIT), Jun 2018

DOI Bib
Using Noisy Binary Search for Differentially Private Anomaly Detection

Daniel Bittner, Anand D. Sarwate, and Rebecca Wright

In Proceedings of the 2nd International Symposium on Cyber Security Cryptography and Machine Learning (CSCML), Jun 2018

DOI Bib
Differentially Private Distributed Principal Component Analysis

Hafiz Imtiaz, and Anand D. Sarwate

In Proceedings of the 43rd IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Apr 2018

DOI Bib
Defending Against Packet-Size Side-Channel Attacks in IoT Networks

Sijie Xiong, Anand D. Sarwate, and Narayan B. Mandayam

In Proceedings of the 43rd IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Apr 2018

DOI Bib
Global Optimality in Inductive Matrix Completion

Mohsen Ghassemi, Naveen Goela, and Anand D. Sarwate

In Proceedings of the 43rd IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Apr 2018

DOI Bib
Improved Algorithms for Differentially Private Orthogonal Tensor Decomposition

Hafiz Imtiaz, and Anand D. Sarwate

In Proceedings of the 43rd IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Apr 2018

DOI Bib
STARK: Structured Dictionary Learning Through Rank-one Tensor Recovery

Mohsen Ghassemi, Zahra Shakeri, Anand D. Sarwate, and Waheed U. Bajwa

In Proceedings of the 7th IEEE International Workshop on Computational Advances in Multi-Sensor Adaptive Processing (CAMSAP), Dec 2017

DOI Bib
Identification of Kronecker-structured dictionaries: An asymptotic analysis

Zahra Shakeri, Anand D. Sarwate, and Waheed U. Bajwa

In Proceedings of the 7th IEEE International Workshop on Computational Advances in Multi-Sensor Adaptive Processing (CAMSAP), Dec 2017

DOI ArXiV Bib
Differentially Private Canonical Correlation Analysis

Hafiz Imtiaz, and Anand D. Sarwate

In Proceedings of the 2017 IEEE Global Conference on Signal and Information Processing (GlobalSIP), Nov 2017

DOI Bib
A Unified Optimization Approach for Sparse Tensor Operations on GPUs

Bangtian Liu, Chengyao Wen, Anand D. Sarwate, and Maryam Mehri Dehnavi

In Proceedings of the 2017 IEEE International Conference on Cluster Computing (CLUSTER), Sep 2017

DOI Bib
Sample Complexity Bounds for Dictionary Learning of Tensor Data

Zahra Shakeri, Waheed U. Bajwa, and Anand D. Sarwate

In Proceedings of the 42nd IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Mar 2017

DOI Bib
Decentralized Independent Vector Analysis

Nikolas Wojtalewicz, Rogers Silva, Vince Calhoun, Anand Sarwate, and Sergey Plis

In Proceedings of the 42nd IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Mar 2017

DOI Bib
Analysis of a Privacy-preserving PCA Algorithm using Random Matrix Theory

Lu Wei, Anand D. Sarwate, Jukka Corander, Alfred Hero, and Vahid Tarokh

In Proceedings of the 2016 IEEE Global Conference on Signal and Information Processing (GlobalSIP), Dec 2016

DOI Bib
Differentially Private Online Active Learning with Applications to Anomaly Detection

Mohsen Ghassemi, Anand D. Sarwate, and Rebecca Wright

In Proceedings of the 9th ACM Workshop on Artificial Intelligence and Security (AISec), Oct 2016

DOI Bib
Data-Dependent Bounds on Network Gradient Descent

Avleen Bijral, Anand D. Sarwate, and Nathan Srebro

In Proceedings of the 54th Annual Allerton Conference on Communication, Control, and Computing, Sep 2016

DOI Bib
A bit of delay is sufficient and stochastic encoding is necessary to overcome online adversarial erasures

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

In Proceedings of the 2016 IEEE International Symposium on Information Theory (ISIT), Jul 2016

DOI ArXiV Bib
Minimax Lower Bounds for Kronecker-Structured Dictionary Learning

Zahra Shakeri, Waheed U. Bajwa, and Anand D. Sarwate

In Proceedings of the 2016 IEEE International Symposium on Information Theory (ISIT), Jul 2016

DOI Bib
Optimal Differential Privacy Mechanisms under Hamming Distortion for Structured Source Classes

Kousha Kalantari, Lalitha Sankar, and Anand D. Sarwate

In Proceedings of the 2016 IEEE International Symposium on Information Theory (ISIT), Jul 2016

DOI Bib
Privacy-preserving source separation for distributed data using independent component analysis

Hafiz Imtiaz, Rogers Silva, Bradley Baker, Sergey M. Plis, Anand D. Sarwate, and Vince D. Calhoun

In Proceedings of the 2016 Annual Conference on Information Science and Systems (CISS), Mar 2016

DOI Bib
Randomized Requantization with Local Differential Privacy

Sijie Xiong, Anand D. Sarwate, and Narayan B. Mandayam

In Proceedings of the 2016 International Conference on Acoustics, Speech and Signal Processing (ICASSP), Mar 2016

DOI Bib
Data Weighted Ensemble Learning for Privacy-Preserving Distributed Learning

Liyang Xie, Sergey M. Plis, and Anand Sarwate

In Proceedings of the 2006 International Conference on Acoustics, Speech and Signal Processing (ICASSP), Mar 2016

DOI Bib
Generalized Opinion Dynamics from Local Optimization Rules

Avhishek Chatterjee, Anand D. Sarwate, and Sriram Vishwanath

In Proceedings of the 49th Asilomar Conference on Signals, Systems, and Computers, Nov 2015

DOI ArXiV Bib
Incentive Schemes For Privacy-Sensitive Consumers

Chong Huang, Lalitha Sankar, and Anand D. Sarwate

In Decision and Game Theory for Security, Nov 2015

DOI Bib Local
Distributed Proportional Stochastic Coordinate Descent with Social Sampling

Mohsen Ghassemi, and Anand D. Sarwate

In Proceedings of the 53rd Annual Allerton Conference on Communication, Control, and Computing, Sep 2015

DOI Bib
Large scale collaboration with autonomy: decentralized data ICA

Bradley Baker, Rogers Silva, Vince D. Calhoun, Anand D. Sarwate, and Sergey Plis

In Proceedings of the IEEE International Workshop on Machine Learning For Signal Processing (MLSP), Sep 2015

DOI Bib
Learning from Data with Heterogeneous Noise using SGD

Shuang Song, Kamalika Chaudhuri, and Anand D. Sarwate

In Proceedings of the Eighteenth International Conference on Artificial Intelligence and Statistics (AISTATS), May 2015

ArXiV Bib
Active dictionary learning for image representation

Tong Wu, Anand D. Sarwate, and Waheed U. Bajwa

In Unmanned Systems Technology XVII, May 2015

DOI Bib Local
CometCloudCare (C^3): Distributed Machine Learning Platform-as-a-Service with Privacy Preservation

Vamsi K. Potluru, Javier Diaz-Montes, Anand D. Sarwate, Sergey M. Plis, Vince D. Calhoun, Barak A. Pearlmutter, and Manish Parashar

In NIPS 2014 Workshop on Distributed Machine Learning and Matrix Computations, Dec 2014

Bib
A Rate-Disortion [sic] Perspective on Local Differential Privacy

Anand D. Sarwate, and Lalitha Sankar

In Proceedings of the 52nd Annual Allerton Conference on Communication, Control and Computation, Sep 2014

DOI Bib Local
Tradeoffs For Task Parallelization In Distributed Optimization

Konstantinos I. Tsianos, Anand D. Sarwate, and Michael G. Rabbat

In Proceedings of the IEEE International Workshop on Machine Learning For Signal Processing (MLSP), Sep 2014

DOI Bib Local
Social Learning and Distributed Hypothesis Testing

Anusha Lalitha, Anand D. Sarwate, and Tara Javidi

In Proceedings of the 2014 IEEE International Symposium on Information Theory (ISIT), Jun 2014

DOI Bib Local
On Measure Concentration of Random Maximum A-Posteriori Perturbations

Francesco Orabona, Tamir Hazan, Anand D. Sarwate, and Tommi Jaakkola

In Proceedings of the 31st International Conference on Machine Learning (ICML), Jun 2014

ArXiV Bib Local
From Private Sites to Big Data Without Compromising Privacy: A Case of Neuroimaging Data Classification

Sergey Plis, Anand Sarwate, J. Turner, M. Arbabshirani, and V. Calhoun

In International Society For Pharmacoeconomics and Outcomes Research (ISPOR) 19th Annual International Meeting, May 2014

DOI Bib
Stochastic Gradient Descent with Differentially Private Updates

Shuang Song, Kamalika Chaudhuri, and Anand D. Sarwate

In Proceedings of the 2013 Global Conference on Signal and Information Processing (GlobalSIP), Dec 2013

DOI Bib Local
Auditing: Active Learning with Outcome-Dependent Query Costs

Sivan Sabato, Anand D. Sarwate, and Nathan Srebro

In Advances in Neural Information Processing Systems (NIPS) 26, Dec 2013

ArXiV Bib Local
Assisted Sampling of Correlated Sources

Vinod M. Prabhakaran, and Anand D. Sarwate

In Proceedings of the 2013 IEEE International Symposium on Information Theory (ISIT), Jul 2013

DOI Bib Local
Near-optimal Differentially Private Principal Components

Kamalika Chaudhuri, Anand D. Sarwate, and Kaushik Sinha

In Advances in Neural Information Processing Systems (NIPS) 25, Dec 2012

Bib
Merging Opinions by Social Sampling of Posteriors

Anand D. Sarwate

In Proceedings of the 50th Annual Allerton Conference on Communication, Control and Computation, Oct 2012

DOI Bib
An AVC perspective on correlated jamming

Anand D. Sarwate

In Proceedings of the International Conference on Signal Processing and Communications (SPCOM), Jul 2012

DOI Bib
Improved Upper Bounds on the Capacity of Binary Channels with Causal Adversaries

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

In Proceedings of the 2012 IEEE International Symposium on Information Theory (ISIT), Jul 2012

DOI Bib
Distributed learning from social sampling

Anand D. Sarwate, and Tara Javidi

In Proceedings of the 46th Annual Conference on Information Sciences and Systems (CISS), Mar 2012

DOI Bib
Opinion Dynamics and Distributed Learning of Distributions

Anand D. Sarwate, and Tara Javidi

In Proceedings of the 49th Annual Allerton Conference on Communication, Control and Computation, Sep 2011

DOI Bib
Protecting Count Queries in Cohort Identification

Staal A. Vinterbo, Anand D. Sarwate, and Aziz Boxwala

In Proceedings of the 2011 AMIA Summit on Clinical Research Informatics, Mar 2011

Bib
Linear Strategies for the Gaussian MAC With User Cooperation

Michéle Wigger, and Anand D. Sarwate

In Proceedings of the 48th Annual Allerton Conference on Communication, Control and Computation, Sep 2010

DOI Bib
Redundancy of exchangeable estimators

Naryana Prasad Santhanam, Mokshay Madiman, and Anand D. Sarwate

In Proceedings of the 48th Annual Allerton Conference on Communication, Control, and Computing, Sep 2010

DOI Bib
Single-Ballot Risk-Limiting Audits Using Convex Optimization

Stephen Checkoway, Anand Sarwate, and Hovav Shacham

In Proceedings of the 2010 Electronic Voting Technology Workshop/Workshop on Trustworthy Elections (EVT/WOTE), Aug 2010

Bib Local
Coding against myopic adversaries

Anand D. Sarwate

In Proceedings of the 2010 Information Theory Workshop (ITW), Aug 2010

DOI Bib
Coding against delayed adversaries

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

In Proceedings of the 2010 IEEE International Symposium on Information Theory (ISIT), Jun 2010

DOI Bib
Gossip and consensus in mobile networks

Anand D. Sarwate, and Alexandros G. Dimakis

In Proceedings of the Third International Workshop on Computational Advances in Multi-Sensor Adaptive Processing (CAMSAP), Dec 2009

DOI Bib
Reaching consensus in wireless networks with probabilistic broadcast

Tuncer Can Aysal, Anand D. Sarwate, and Alexandros G. Dimakis

In Proceedings of the 47th Annual Allerton Conference on Communication, Control, and Computation, Sep 2009

DOI Bib
Some observations on limited feedback for multiaccess channels

Anand D. Sarwate, and Michael Gastpar

In Proceedings of the 2009 IEEE International Symposium on Information Theory (ISIT), Jun 2009

DOI Bib
The Impact of Mobility on Gossip Algorithms

Anand D. Sarwate, and Alexandros G. Dimakis

In Proceedings of the 28th Annual International Conference on Computer Communications (INFOCOM), Apr 2009

DOI Bib
Broadcast Gossip Algorithms: Design and Analysis for Consensus

Tuncer Can Aysal, Mehmet Ercan Yildiz, Anand D. Sarwate, and Anna Scaglione

In Proceedings of the 47th IEEE Conference on Decision and Control (CDC), Dec 2008

DOI Bib
Arbitrarily dirty paper coding and applications

Anand D. Sarwate, and M. Gastpar

In Proceedings of the 2008 IEEE International Symposium on Information Theory (ISIT), Jul 2008

DOI Bib
Adversarial interference models for multiantenna cooperative systems

Anand D. Sarwate, and Michael Gastpar

In Proceedings of the 42nd Annual Conference on Information Sciences and Systems (CISS), Mar 2008

DOI Bib Local
Rateless coding with partial CSI at the decoder

Anand D. Sarwate, and Michael Gastpar

In Proceedings of the 2007 Information Theory Workshop (ITW), Sep 2007

DOI Bib
Spatial filtering in sensor networks using computation codes

Anand D. Sarwate, Bobak Nazer, and Michael Gastpar

In Proceedings of the 2007 IEEE Statistical Signal Processing Workshop (SSP), Aug 2007

DOI Bib Local
Channels with nosy “noise”

Anand D. Sarwate, and Michael Gastpar

In Proceedings of the 2007 IEEE International Symposium on Information Theory (ISIT), Jun 2007

DOI Bib
Using zero-rate feedback on binary additive channels with individual noise sequences

Krishnan Eswaran, Anand D. Sarwate, Anant Sahai, and Michael Gastpar

In Proceedings of the 2007 IEEE International Symposium on Information Theory (ISIT), Jun 2007

DOI Bib
Randomization for robust communication in networks, or “Brother, can you spare a bit?”

Anand D. Sarwate, and Michael Gastpar

In Proceedings of the 44th Annual Allerton Conference on Communication, Control and Computation, Sep 2006

Bib
Randomization bounds on Gaussian arbitrarily varying channels

Anand D. Sarwate, and Michael Gastpar

In Proceedings of the 2006 IEEE International Symposium on Information Theory (ISIT), Jul 2006

DOI Bib
Geographic Gossip : Efficient Aggregation for Sensor Networks

Alexandros D.G. Dimakis, Anand D. Sarwate, and Martin J. Wainwright

In 5th International Symposium on Information Processing in Sensor Networks (IPSN), Apr 2006

DOI Bib
Fading observation alignment via feedback

Anand D. Sarwate, and Michael Gastpar

In Proceedings of the Fourth International Symposium on Information Processing in Sensor Networks (IPSN), Apr 2005

DOI Bib
Estimation from Misaligned Observations with Limited Feedback

Anand D. Sarwate, and Michael Gastpar

In Proceedings of the 39th Conference on Information Sciences and Systems (CISS), Mar 2005

Bib

Theses

Robust and adaptive communication under uncertain interference

Anand D. Sarwate

University of California, Berkeley, Jul 2008

Bib Local
Observation Uncertainty in Gaussian Sensor Networks

A. D. Sarwate

University of California, Berkeley, Dec 2005

Bib Local