Yanina Shkel
Postdoctoral Scholar

Department of Electrical Engineering
Princeton University

Department of Electrical and Computer Engineering
Coordinated Science Laboratory
University of Illinois at Urbana-Champaign

E-mail: yshkel [at] princeton [dot] edu
E-mail: yshkel2 [at] illinois [dot] edu


RESEARCH


I am broadly interested in identifying laws which govern the behavior of information in both engineered and naturally occurring systems, and using these laws to better understand the capabilities of such systems. My most recent research focuses on points of connection between machine learning, statistics, and information theory. I am particularly interested in understanding the impact of data compression constraints on learning and prediction, and vice versa.

ABOUT


I am a postdoctoral fellow with the NSF Center for Science of Information where I have the pleasure of collaborating with Sergio Verdú and Maxim Raginsky. I can be found with some (non-zero) probability at Princeton University, and with some (non-zero) probability at UIUC.

I completed my PhD at the University of Wisconsin-Madison under the supervision of Stark C. Draper. Before graduate school I also worked as a developer for Morningstar Inc. where I administered databases containing and processing large amounts of financial data. More recently, I was an intern at 3M Corporate Research Labs where I utilized my background in computation and information sciences for materials and product driven needs of 3M.

I am on the job market this year. Take a look at my recent work below.

PUBLICATIONS


  • Yanina Shkel, Maxim Raginsky, and Sergio Verdú
    Universal lossy compression under logarithmic loss
    Submitted [PDF]

  • Yanina Shkel and Sergio Verdú
    A single-shot approach to lossy source coding under logarithmic loss
    Submitted [PDF]

    Preliminary version appeared in 2016 Proceedings of IEEE International Symposium on Information Theory, Barcelona, Spain

  • Yanina Shkel and Sergio Verdú
    A Coding Theorem for f-Separable Distortion Measures
    [PDF]

    Based on an invited talk in 2016 Information Theory and Applications Workshop, La Jolla, CA

  • Yanina Shkel, Vincent Y. F. Tan, and Stark C. Draper
    Unequal message protection: asymptotic and non-asymptotic tradeoffs
    IEEE Transactions on Information Theory, vol. 61, no. 10, pp. 5396 - 5416, 2015
    [LINK]

    Preliminary versions appeared in 2014 Proceedings of IEEE International Symposium on Information Theory, Honolulu, HI and in 2013 Proceedings of IEEE International Symposium on Information Theory, Istanbul, Turkey

  • Yanina Shkel, Vincent Y. F. Tan, and Stark C. Draper
    Second-order coding rate for m-class source-channel codes
    Proceedings of the 53rd Allerton Conference on Communication, Control, and Computing, 2015
    [LINK]

  • Yanina Shkel, Vincent Y. F. Tan, and Stark C. Draper
    On mismatched unequal message protection for finite block length joint source-channel coding
    2013 Proceedings of IEEE International Symposium on Information Theory, Istanbul, Turkey
    [LINK]

  • Bobak Nazer, Yanina Shkel, and Stark C. Draper
    The AWGN Red Alert Problem
    IEEE Transactions on Information Theory, vol. 59, no. 4, pp. 2188 - 2200, 2013
    [LINK]

  • Yanina Shkel, Stark C. Draper, and Bobak Nazer
    On the cooperative red alert exponent for the AWGN-MAC with feedback
    Proceedings of the 49th Allerton Conference on Communication, Control, and Computing, 2011
    [LINK]

  • Yanina Shkel and Stark C. Draper
    Cooperative reliability for streaming multiple access
    2010 Proceedings of IEEE International Symposium on Information Theory, Austin, TX
    [LINK]