Rishav Chourasia

Databases Lab 3,

NUS School of Computing,

COM1, 13 Computing Drive

Singapore 117417.

I am a final-year Ph.D. student at NUS School of Computing. Before that, I worked at Amazon India as a Software Development Engineer with Transaction Risk Management team. I had previously obtained my Bachelor’s degree in Computer Science and Engineering from the Indian Institute of Technology, Guwahati.

Currently, I am working on Differentially Private Machine Learning and Machine Unlearning algorithms.

news

May 18, 2023	I’ll be giving a talk on my ICML 2023 paper Forget Unlearning: Towards True Data Deletion in Machine Learning at FORC 2023 at Stanford University.
May 10, 2022	I’ll be interning at Google Brain this summer, collaborating with Krishnamurthy Dvijotham and Abhradeep Thakurta in the Privacy and Security research team.
Sep 28, 2021	My paper on Differential Privacy Dynamics of Langevin Diffusionand Noisy Gradient Descent got accepted as spotlight at NeurIPS, 2021 (among 3% of submissions).
Jan 22, 2021	Updated my blog on Differential Privacy in ML!

selected publications

ICML 2023
& FORC 2023

Forget Unlearning: Towards True Data-Deletion in Machine Learning

Rishav Chourasia, and Neil Shah

In Proceedings of the 40th International Conference on Machine Learning, 2023

Bib PDF

@inproceedings{pmlr-v163-chourasia23forget,
  bibtex_show = {true},
  abbr = {ICML 2023},
  abbr2 = {& FORC 2023},
  selected = {true},
  title = {Forget Unlearning: Towards True Data-Deletion in Machine Learning},
  author = {Chourasia, Rishav and Shah, Neil},
  booktitle = {Proceedings of the 40th International Conference on Machine Learning},
  year = {2023},
  volume = {163},
  series = {Proceedings of Machine Learning Research},
  publisher = {PMLR},
  pdf = {chourasia2023forget.pdf}
}

NeurIPS 2021
(spotlight)

Differential Privacy Dynamics of Langevin Diffusion and Noisy Gradient Descent

Rishav Chourasia, Jiayuan Ye, and Reza Shokri

In Advances in Neural Information Processing Systems, 2021

Bib PDF

@inproceedings{NIPS2021_7c6c1a7b,
  bibtex_show = {true},
  author = {Chourasia, Rishav and Ye, Jiayuan and Shokri, Reza},
  abbr = {NeurIPS 2021},
  abbr2 = {(spotlight)},
  selected = {true},
  booktitle = {Advances in Neural Information Processing Systems},
  editor = {Ranzato, M. and Beygelzimer, A. and Liang, P.S. and Vaughan, J.W. and Dauphin, Y.},
  pages = {},
  publisher = {Curran Associates, Inc.},
  title = {Differential Privacy Dynamics of Langevin Diffusion and Noisy Gradient Descent},
  url = {https://proceedings.neurips.cc/paper/2021/file/7c6c1a7bfde175bed616b39247ccace1-Paper.pdf},
  volume = {34},
  year = {2021},
  pdf = {NIPS2021_7c6c1a7b.pdf}
}