Siddarth Asokan

RSDE @ MSRI, Bangalore | Ph.D. @ RBCCPS, IISc, Bangalore.


Hi! I’m a Research Software Development Engineer (RSDE) at the Microsoft Research Lab (MSRI) in Bangalore, India, as part of Manik Varma’s group, and currently exploring the world of text-based generative models (or Tiny/Small/Large Language Models, as people call them these days) in the context of eXtreme Classification. Previously, I was an interdisciplinary Direct-Ph.D. scholar at the Robert Bosch Center for Cyber-Physical Systems (RBCCPS) at the Indian Institute of Science, Bangalore. I worked at the Spectrum Lab in the Department of Electrical Engineering, under the supervision of Prof. Chandra Sekhar Seelamantula. Before that, I was at M.S. Ramaiah Institute of Technology (MSRIT), Bangalore, where I completed my Bachelors in Engineering in Electronics and Communications. Check out my full CV or publications. Amongst other things, I love photography and Misty, my doggo!!

My research interests are broadly in the area of machine learning and generative modeling, with a focus, during my Ph.D., on generative adversarial networks (GANs). My Ph.D. was on building theoretical foundations for analyzing GANs, leveraging insights from classical signal processing, and designing network architectures motivated by those findings. Recently, I’ve (like everyone else that worked with GANs) also been exploring score-based diffusion and normalizing-flow models!

Throughout my Ph.D. I’ve been graciously funded by the Microsoft Research Ph.D. Fellowship in 2018, the RBCCPS Ph.D. Fellowship in 2020-2021, and 2021-2022, and the Qualcomm Innovation Fellowship in 2019, 2021, 2022 and 2023!

Looking to collaborate or know more about my research?
Reach out to me at [FirstLetterOfFirstName][LastName] (at) microsoft (dot) com


Feb 06, 2024 My Ph.D. Thesis was awarded the Prof. Satish Dhawan Research Award 2023!
Dec 14, 2023 Two papers have been accepted to ICASSP 2024! :tada: .See you in Seoul, South Korea
Nov 06, 2023 Joined Microsoft Research Lab India as an RSDE! Looking forward to working on XC!!
Sep 15, 2023 Successfully defended my Ph.D. Thesis.
Jun 30, 2023 Selected as a Super-Winner for the Qualcomm Innovation Fellowship 2023! :tada:

selected publications

  1. NeurIPS 20
    Teaching a GAN What Not to Learn
    S. Asokan , and C. S. Seelamantula
    In Advances in Neural Information Processing Systems (NeurIPS) , 2020
  2. ICASSP 23
    A game of snakes and GANs
    S. Asokan , F. S. Mohammed , and C. S. Seelamantula
    The Proceedings on the IEEE International Conference of Acoustics, Speech and Signal Processing (ICASSP), 2023
  3. CVPR 23
    Spider GANs: Leveraging friendly neighbors to accelerate GAN training
    S. Asokan , and C. S. Seelamantula
    The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2023
  4. JMLR
    Euler-Lagrange Analysis of Generative Adversarial Networks
    S. Asokan , and C. S. Seelamantula
    Journal of Machine Learning Research (JMLR), 2023
  5. arXiv
    GANs Settle Scores!
    S. Asokan , N. Shetty , A. Srikanth , and 1 more author
    arXiv preprints, arXiv:2306.01654, 2023
  6. arXiv
    Data Interpolants – That’s What Discriminators in Higher-order Gradient-regularized GANs Are
    S. Asokan , and C. S. Seelamantula
    arXiv preprints, arXiv:2306.01654, 2023
  7. PhD Thesis
    On the Optimality of Generative Adversarial Networks — A Variational Perspective
    S. Asokan
    In partial fulfillment of the requirements for the Degree of Doctor of Philosophy, IISc , 2023
  8. ICASSP 24
    Momentum-imbued Langevin Dynamics (MILD) for Faster Sampling
    N. Shetty ,  M. Bandla ,  N. Neema , and 2 more authors
    The Proceedings on the IEEE International Conference of Acoustics, Speech and Signal Processing (ICASSP), 2024
  9. ICASSP 24
    Variational Analysis of Adversarial Regularization for Solving Inverse Problems
    A. S. Bhandiwad ,  A. J. Kamath , S. Asokan , and 1 more author
    The Proceedings on the IEEE International Conference of Acoustics, Speech and Signal Processing (ICASSP), 2024