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:
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.
May 28, 2023 Just returned from a really fabulous workshop on Information-Theoretic Methods for Trustworthy Machine Learning at the Simons Institute for the Theory of Computing at UC Berkeley. It was weird to wander around a place I lived 20 years ago but really nice to see old friends and meet new people.
May 19, 2023 Finally mostly ported everything over to the new site… :construction:
Jul 26, 2022 Some new work:
Jul 1, 2022 New grant! RINGS: REALTIME: Resilient Edge-cloud Autonomous Learning with Timely Inferences, co-PIs Roy D. Yates, Waheed U. Bajwa, and Dipankar Raychaudhuri. We will be looking at issues in adaptive edge-cloud assisted ML-based services from the ground-up.