Hi! I'm

Siddarth Asokan.

RDSE @ Microsoft Research, Bangalore
PhD @ IISc, Bangalore

Siddarth Asokan

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

``Vigyan'', No. 9,

Microsoft Research Lab,

Lavelle Road, Bengaluru,

Karnataka, 560001

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 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 work 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

news

Sep 15, 2023	Successfully defended my Ph.D. Thesis. #PhDone!
Jun 30, 2023	Selected as a Super-Winner for the Qualcomm Innovation Fellowship 2023
May 11, 2023	Successfully submitted my Ph.D. Thesis!!
Apr 28, 2023	Successfully completed my Ph.D. Colloquium!!
Mar 1, 2023	Our paper has been accepted at CVPR 2023! See you in Vancouver, Canada

selected publications

NeurIPS 20

Teaching a GAN What Not to Learn

S. Asokan, and C. S. Seelamantula

In Advances in Neural Information Processing Systems (NeurIPS) 2020

Bib HTML PDF

@inproceedings{RumiGAN20,
  author = {Asokan, S. and Seelamantula, C.~S.},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS) },
  pages = {3964--3975},
  title = {Teaching a {GAN} What Not to Learn},
  volume = {33},
  year = {2020},
}

NeurIPSW 22

Bridging the Gap Between Coulomb GAN and Gradient-regularized WGAN

S. Asokan, and C. S. Seelamantula

In Proceedings on "The Symbiosis of Deep Learning and Differential Equations - II" at NeurIPS Workshops 2022

Bib HTML PDF

@inproceedings{RBFCoulombGAN22,
  title = {Bridging the Gap Between {C}oulomb {GAN} and Gradient-regularized {WGAN}},
  author = {Asokan, S. and Seelamantula, C.~S.},
  booktitle = {Proceedings on "The Symbiosis of Deep Learning and Differential Equations - II" at NeurIPS Workshops},
  year = {2022},
}

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

Bib HTML

@article{SnakeGAN23,
  author = {Asokan, S. and Mohammed, F. S. and Seelamantula, C. S.},
  journal = {The Proceedings on the IEEE International Conference of Acoustics, Speech and Signal Processing (ICASSP)},
  title = {A game of snakes and {GAN}s},
  year = {2023}
}

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

arXiv Bib HTML PDF Website

@article{SpiderGAN23,
  author = {Asokan, S. and Seelamantula, C. S.},
  journal = {The IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
  title = {Spider {GANs}: {L}everaging friendly neighbors to accelerate {GAN} training},
  year = {2023},
}

JMLR

Euler-Lagrange Analysis of Generative Adversarial Networks

S. Asokan, and C. S. Seelamantula

Journal of Machine Learning Research (JMLR) 2023

Bib HTML PDF

@article{ELeGANt23,
  author = {Asokan, S. and Seelamantula, C. S.},
  journal = {Journal of Machine Learning Research (JMLR)},
  pages = {1--100},
  title = {Euler-Lagrange Analysis of Generative Adversarial Networks},
  year = {2023},
}

arXiv

GANs Settle Scores!

S. Asokan, N. Shetty, A. Srikanth, and 1 more author

arXiv preprints, arXiv:2306.01654 2023

Bib HTML PDF

@article{ScoreFloWGANs23,
  title = {{GANs} Settle Scores!},
  author = {Asokan, S. and Shetty, N. and Srikanth, A. and Seelamantula, C. S.},
  year = {2023},
  eprint = {2306.01654},
  journal = {arXiv preprints, arXiv:2306.01654},
  publisher = {arXiv},
}

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

Bib HTML PDF

@article{PolyGAN23,
  title = {Data Interpolants -- That's What Discriminators in Higher-order Gradient-regularized {GANs} Are},
  author = {Asokan, S. and Seelamantula, C. S.},
  year = {2023},
  eprint = {2306.01654},
  journal = {arXiv preprints, arXiv:2306.01654},
  publisher = {arXiv},
}

NeurIPSW 23

\f\-GANs Settle Scores!

S. Asokan, N. Shetty, A. Srikanth, and 1 more author

In NeurIPS 2023 Workshop on Diffusion Models 2023

HTML PDF
NeurIPSW 23

ELeGANt: An Euler-Lagrange Analysis of Wasserstein Generative Adversarial Networks

S. Asokan, and C. S. Seelamantula

In The Symbiosis of Deep Learning and Differential Equations III 2023

HTML PDF

Tweets by Siddarth95