Suhas Diggavi

Suhas Diggavi

Suhas Diggavi
Professor
Primary Area: Signals and Systems

Office: 6731J, Boelter Hall
Phone: (310) 206-5171
E-mail: suhas@ee.ucla.edu
Web: http://licos.ee.ucla.edu/

 
Research Interests:
Information theory and its applications to learning, cyber-physical systems, security & privacy, wireless networks, bio-informatics and neuroscience.
 
Teaching:
Information Theory (ECE 231A), Foundations of Statistical Machine Learning (ECE 246), Stochastic Processes (ECE 241A), Network Information Theory (ECE 231B), Introduction to Communication Systems (ECE 132A), Introduction to Machine Learning (M146).

 

Selected Awards and Recognitions
2021     Guggenheim Foundation Fellow (Natural Sciences)
2021     ACM Computer and Communication Security (CCS) Best Paper Award
2021     Facebook Research Award
2020     Amazon Research Award
2019     Google Faculty Research Award
2015     IEEE Distinguished Lecturer, IEEE Information theory society
2013     IEEE Information Theory Society & Communications Society Joint Paper Award
2013     ACM International Symposium on Mobile Ad Hoc Networking and Computing (MobiHoc) Best Paper Award
2013     IEEE Fellow
2006     IEEE Donald G. Fink Prize Paper Award

 

Selected Recent Publications
  • K. Ozkara, N. Singh, D. Data, Suhas N. Diggavi, “QuPeD: Quantized Personalization via Distillation with Applications to Federated Learning,” Neural Information Processing Systems (NeurIPS) 2021.
  • A M. Girgis, D. Data, S N. Diggavi, A T. Suresh, P. Kairouz, “On the Renyi Differential Privacy of the Shuffle Model,” in ACM Computer and Communication Security (CCS) 2021.
  • N. Singh, D. Data, J. George, S N. Diggavi, “SQuARM-SGD: Communication-Efficient Momentum SGD for Decentralized Optimization”. IEEE Journal of Selected Areas in Information Theory 2(3): 954-969 (2021)
  • A M. Girgis, D. Data, S N. Diggavi, “Renyi Differential Privacy of the Subsampled Shuffle Model in Distributed Learning,” Neural Information Processing Systems (NeurIPS) 2021.
  • A M. Girgis, D. Data, K. Chaudhuri, C. Fragouli, S N. Diggavi, “Successive Refinement of Privacy,” IEEE Journal of Selected Areas in Information Theory 1(3): 745-759 (2020)
  • A M. Girgis, D. Data, S N. Diggavi, P. Kairouz, A T. Suresh, “Shuffled Model of Differential Privacy in Federated Learning,” International Conference on Artificial Intelligence and Statistics (AISTATS), Proceedings of Machine Learning Research (PMLR), pp 2521-2529, 2021.
  • D. Data, S N. Diggavi, “Byzantine-Resilient High-Dimensional SGD with Local Iterations on Heterogeneous Data,” Proceedings International Conference on Machine Learning (ICML), 2021. See also Arxiv https://arxiv.org/abs/2006.1304
  • P. Nikolopoulos, S R. Srinivasavaradhan, T. Guo, C. Fragouli, S N. Diggavi, “Group testing for connected communities,” International Conference on Artificial Intelligence and Statistics (AISTATS), Proceedings of Machine Learning Research (PMLR), pp: 2341-2349, 2021.
  • S R. Srinivasavaradhan, M. Du, S N. Diggavi and C. Fragouli, “Algorithms for reconstruction over single and multiple deletion channels,” IEEE Transactions on Information Theory, 2020.
  • D. Joshi, S. Mao, S. Kannan and S N. Diggavi, “QAlign: Aligning nanopore reads accurately using current-level modeling,” Bioinformatics, 2020.
  • D. Basu, D. Data, C. Karakus, S N. Diggavi, “Qsparse-local-SGD: Distributed SGD with Quantization, Sparsification and Local Computations,” in Neural Information Processing Systems (NeurIPS), pp 14668-14679, 2019.
  • C. Karakus, Y. Sun, S N. Diggavi and W. Yin, “Redundancy Techniques for Straggler Mitigation in Distributed Optimization and Learning,” Journal of Machine Learning Research (JMLR), vol 20, pp 72;1–72:47, April 2019.
  • W. Mao, S N. Diggavi and S. Kannan, “Models and information-theoretic bounds for nanopore sequencing,” IEEE Transactions on Information Theory, volume 64, number 4, pp 3216–3236, April 2018.
  • C. Karakus, Y. Sun, S N. Diggavi and W. Yin, “Straggler Mitigation in Distributed Optimization Through Data Encoding,” in Neural Information Processing Systems (NIPS), pp 5440-5448, Dec. 2017.
  • J. Hachem, N. Karamchandani and S N. Diggavi, “Coded caching for multi-level popularity and access,” IEEE Transactions on Information Theory, volume 63, number 5, pp 3108-3141, May 2017.
  • N. Karamchandani, U. Niesen, M. Maddah-Ali, S N. Diggavi, “Hierarchical Coded Caching,” IEEE Transactions on Information Theory, volume 62, number 6, pp 3212-3229, June 2016.
  • C. Fragouli, V. Prabhakaran, L. Czap and S N. Diggavi, “Wireless Network Security: Building on Erasures,,” Proceedings IEEE, vol 103, number 10, pp 1826-1840, October 2015.
  • S. Avestimehr, S N. Diggavi, C. Tian and D. Tse, “An approximation approach to network information theory”, monograph, NOW publishers, December 2015.
  • H. Fawzi, P. Tabuada and S N. Diggavi, “Secure estimation and control for cyber-physical systems under adversarial attacks,” IEEE Transactions on Automatic Control, vol 59, number 6, pp 1454- 1467, June 2014.
  • S. Avestimehr, S N. Diggavi and D N C. Tse, “Wireless network information flow: a deterministic approach,” IEEE Transactions on Information Theory, vol 57, number 4, pp. 1872-1905, April 2011
  • C. Tian, S. Mohajer and S N. Diggavi, “Approximating the Gaussian Multiple Description Rate Region Under Symmetric Distortion”, IEEE Transactions on Information Theory, vol 55, issue 8, pp. 3869–3891, August 2009.
  • S N. Diggavi, A R. Calderbank, S. Dusad and N. Al-Dhahir, “Diversity Embedded Space-Time Codes,” IEEE Transactions on Information Theory, Volume 54, Issue 1, pp. 33–50, January 2008.
  • S N. Diggavi, M. Grossglauser and D N C. Tse, “One-dimensional mobility increases capacity of wireless adhoc networks,” IEEE Transactions on Information Theory, Volume 51, Issue 11, pp. 3947–3854, November 2005.
  • S N. Diggavi, N J A. Sloane and V A. Vaishampayan, “Asymmetric Multiple Description Lattice Vector Quantizers,” IEEE Transactions on Information Theory, vol 48, number 1, pp. 174–191, January 2002.
  • S N. Diggavi and T M. Cover, “Worst additive noise under covariance constraints,” IEEE Transactions on Information Theory, November 2001, vol 47, number 7, pp. 3072–3081.
  • S N. Diggavi, “On achievable performance over spatial diversity fading channels,” IEEE Transactions on Information Theory, vol 47, number 1, pp. 308–325, January 2001.