Image of Ravi

ECE 359
Department of ECE
University of Arizona
1230 E. Speedway Blvd.
Tucson, AZ 85721
tandonr@arizona.edu
Google Scholar
Professor
Craig M. Berge Faculty Fellow
Department of Electrical and Computer Engineering
University of Arizona


Current research interests:
- Trustworthy Machine Learning
- Privacy and Security in AI
- Distributed and Federated Learning
- Information Theory

Biography: Ravi Tandon is a Professor in the Department of ECE at the University of Arizona, where he holds a Craig M. Berge Faculty Fellowship and a courtesy appointment in Applied Mathematics. He received the Ph.D. degree in ECE from the University of Maryland, College Park in 2010 and B.Tech. degree in Electrical Engineering from IIT Kanpur in 2004. He was a post-doctoral research associate at Princeton University from 2010-2012. From 2012-2015, he was a Research Assistant Professor at Virginia Tech. Dr Tandon is a recipient of a NSF CAREER Award in 2017, the 2018 Keysight Early Career Professor Award, a Best Paper Award at 2011 IEEE Globecom conference. He has served as an Associate Editor for IEEE Transactions on Information Theory, IEEE Transactions on Wireless Communications and the IEEE Transactions on Communications.

Selected Recent Papers and Pre-prints:

  1. Conformal Sparsification for Bandwidth-Efficient Edge-Cloud Speculative Decoding
    P. Bhattacharjee, F. Tian, M. Zhong, G. Zhang, O Simeone and R. Tandon
    Neural Information Processing Systems (NeurIPS) AI4NextG Workshop, 2025.
  2. Can Multiple Responses from an LLM Reveal the Sources of Its Uncertainty?
    Y. Nan, P. He, R. Tandon and H. Xu
    Conference on Empirical Methods in Natural Language Processing (EMNLP), 2025.
  3. Speeding up Speculative Decoding via Sequential Approximate Verification
    M. Zhong, N. Teku and and R. Tandon
    ICML Workshop on Efficient Systems for Foundation Models, 2025.
  4. Fine-Grained Uncertainty Quantification via Collisions
    J. Friedbaum, S. Adiga, and R. Tandon
    IEEE Transactions on Information Theory, Pre-print, 2025.
  5. SPLITZ: Certifiable Robustness via Split Lipschitz Randomized Smoothing
    M. Zhong and R. Tandon
    IEEE Transactions on Information Forensics and Security, 2025.
  6. Trustworthy Actionable Perturbations
    J. Friedbaum, S. Adiga, and R. Tandon
    International Conference on Machine Learning (ICML), July 2024.
  7. Latency-Distortion Tradeoffs in Communicating Classification Results over Noisy Channels
    N. Teku, S. Adiga and R. Tandon
    IEEE Transactions on Communications, 2024.
  8. Generalization Bounds for Neural Belief Propagation Decoders
    S. Adiga, X. Xiao, R. Tandon, B. Vasić and T. Bose
    IEEE Transactions on Information Theory, 2024.