I am a third year PhD student in Department of Computer Science, University of Maryland, College Park, working with Prof. David W. Jacobs. Prior to joining UMD, I was a Senior Software Developer at Oracle Server Technologies Group, India. I received my Master's degree in Systems Science And Automation from IISc, Bangalore, India. I graduated with Bachelor's degree in Electrical Engineering from MNNIT, Allahabad, India.

I mainly work on the intersection of Deep Learning, Computer Vision and Optimization.


  1. Stabilizing Adversarial Nets with Prediction Methods.
    Abhay Kumar Yadav*, Sohil Shah*, Zheng Xu, David W. Jacobs, and Tom Goldstein.
    Under review as a conference paper at International Conference on Learning Representations (ICLR), 2018. (*equal contribution)
    [ Paper ]
  2. Biconvex Relaxation for Semidefinite Programming in Computer Vision.
    Sohil Shah*, Abhay Kumar Yadav*, Carlos D. Castillo, David W. Jacobs, Christoph Studer, and Tom Goldstein.
    In Proc. European Conference on Computer Vision (ECCV), 2016. (*equal contribution)
    [ Paper ]
  3. New Methods for Handling Binary Constraints .
    Abhay Kumar Yadav, R. Ranjan, U. Mahbub and M.C. Rotkowitz.
    In Proceedings of the 54th Annual Allerton Conference on Communication, Control, and Computing, 2016. (Oral)
    [ Paper ]
  4. Automated Inference with Adaptive Batches.
    Soham De, Abhay Kumar Yadav, David Jacobs, and Tom Goldstein.
    In The 20th International Conference on Artificial Intelligence and Statistics (AISTATS), 2017. (Oral)
    [ Paper ]
  5. Son of Zorn's Lemma: Targeted Style Transfer Using Instance-aware Semantic Segmentation.
    Carlos Castillo, Soham De, Xintong Han, Bharat Singh, Abhay Kumar Yadav, and Tom Goldstein.
    In The 42nd IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2017. (Oral, All authors contributed equally)
    [ Paper ]
  6. Maximum Entropy Model Based Classification with Feature Selection.
    Ambedkar Dukkipati, Abhay Kumar Yadav, M. Narasimha Murty.
    In International Conference on Pattern Recognition (ICPR), 2010.
    [ Paper ]