Publications

You can also find my articles on my Google Scholar profile.

Publications


Selective pre-training for private fine-tuning

Published in Transactions on Machine Learning Research (TMLR), 2024

Recommended citation: Da Yu, Sivakanth Gopi, Janardhan Kulkarni, Zinan Lin, Saurabh Naik, Tomasz Religa, Jian Yin, Huishuai Zhang, "Selective pre-training for private fine-tuning." Transactions on Machine Learning Research (TMLR), 2024.
Download Paper

Generalized GM-MDS: Polynomial Codes are Higher Order MDS

Published in Proceedings of the 56th Annual ACM Symposium on Theory of Computing, 2024

Recommended citation: Joshua Brakensiek, Manik Dhar, Sivakanth Gopi, "Generalized GM-MDS: Polynomial Codes are Higher Order MDS." Proceedings of the 56th Annual ACM Symposium on Theory of Computing, 2024.
Download Paper

Differentially private synthetic data via foundation model apis 2: Text

Published in International Conference on Machine Learning (ICML), 2024

Recommended citation: Chulin Xie, Zinan Lin, Arturs Backurs, Sivakanth Gopi, Da Yu, Huseyin Inan, Harsha Nori, Haotian Jiang, Huishuai Zhang, Yin Lee, et al., "Differentially private synthetic data via foundation model apis 2: Text." International Conference on Machine Learning (ICML), 2024.
Download Paper

Textbooks are all you need

Published in arXiv preprint arXiv:2306.11644, 2023

Recommended citation: Suriya Gunasekar, Yi Zhang, Jyoti Aneja, Caio Mendes, Allie Del, Sivakanth Gopi, Mojan Javaheripi, Piero Kauffmann, Gustavo Rosa, Olli Saarikivi, et al., "Textbooks are all you need." arXiv preprint arXiv:2306.11644, 2023.
Download Paper

Private convex optimization in general norms

Published in Proceedings of the 2023 Annual ACM-SIAM Symposium on Discrete Algorithms (SODA), 2023

Recommended citation: Sivakanth Gopi, Yin Lee, Daogao Liu, Ruoqi Shen, Kevin Tian, "Private convex optimization in general norms." Proceedings of the 2023 Annual ACM-SIAM Symposium on Discrete Algorithms (SODA), 2023.

Phi-2: The surprising power of small language models

Published in Microsoft Research Blog, 2023

Recommended citation: Mojan Javaheripi, S{\'e}bastien Bubeck, Marah Abdin, Jyoti Aneja, Sebastien Bubeck, Caio Mendes, Weizhu Chen, Allie Del, Ronen Eldan, Sivakanth Gopi, et al., "Phi-2: The surprising power of small language models." Microsoft Research Blog, 2023.
Download Paper

Differentially private fine-tuning of language models

Published in International Conference on Learning Representations (ICLR), 2022

Journal version: Journal of Privacy and Confidentiality, 2024

Recommended citation: Da Yu, Saurabh Naik, Arturs Backurs, Sivakanth Gopi, Huseyin Inan, Gautam Kamath, Janardhan Kulkarni, Yin Lee, Andre Manoel, Lukas Wutschitz, et al., "Differentially private fine-tuning of language models." International Conference on Learning Representations (ICLR), 2022.
Download Paper

Differentially private n-gram extraction

Published in Advances in neural information processing systems, 2021

Recommended citation: Kunho Kim, Sivakanth Gopi, Janardhan Kulkarni, Sergey Yekhanin, "Differentially private n-gram extraction." Advances in neural information processing systems, 2021.
Download Paper

Locally private hypothesis selection

Published in Conference on Learning Theory, 2020

Recommended citation: Sivakanth Gopi, Gautam Kamath, Janardhan Kulkarni, Aleksandar Nikolov, Zhiwei Wu, Huanyu Zhang, "Locally private hypothesis selection." Conference on Learning Theory, 2020.
Download Paper

Differentially private set union

Published in International Conference on Machine Learning, 2020

Journal version: Journal of Privacy and Confidentiality, 2021

Recommended citation: Sivakanth Gopi, Pankaj Gulhane, Janardhan Kulkarni, Judy Shen, Milad Shokouhi, Sergey Yekhanin, "Differentially private set union." International Conference on Machine Learning, 2020.

Maximally recoverable LRCs: A field size lower bound and constructions for few heavy parities

Published in Proceedings of the Thirtieth Annual ACM-SIAM Symposium on Discrete Algorithms (SODA), 2019

Journal version: IEEE Transactions on Information Theory, 2020

Recommended citation: Sivakanth Gopi, Venkatesan Guruswami, Sergey Yekhanin, "Maximally recoverable LRCs: A field size lower bound and constructions for few heavy parities." Proceedings of the Thirtieth Annual ACM-SIAM Symposium on Discrete Algorithms (SODA), 2019.
Download Paper

CSPs with global modular constraints: algorithms and hardness via polynomial representations

Published in Proceedings of the 51st Annual ACM SIGACT Symposium on Theory of Computing, 2019

Journal version: SIAM Journal of Computing, 2022

Recommended citation: Joshua Brakensiek, Sivakanth Gopi, Venkatesan Guruswami, "CSPs with global modular constraints: algorithms and hardness via polynomial representations." Proceedings of the 51st Annual ACM SIGACT Symposium on Theory of Computing, 2019.
Download Paper

Lower bounds for 2-query LCCs over large alphabet

Published in Approximation, Randomization, and Combinatorial Optimization. (APPROX RANDOM 2017), 2017

Recommended citation: Arnab Bhattacharyya, Sivakanth Gopi, Avishay Tal, "Lower bounds for 2-query LCCs over large alphabet." Approximation, Randomization, and Combinatorial Optimization. (APPROX RANDOM 2017), 2017.
Download Paper

Locally testable and locally correctable codes approaching the Gilbert-Varshamov bound

Published in Proceedings of the 2017 Annual ACM-SIAM Symposium on Discrete Algorithms (SODA), 2017

Journal version: IEEE Transactions on Information Theory, 2018

Recommended citation: Sivakanth Gopi, Swastik Kopparty, Rafael Oliveira, Noga Ron-Zewi, Shubhangi Saraf, "Locally testable and locally correctable codes approaching the Gilbert-Varshamov bound." Proceedings of the 2017 Annual ACM-SIAM Symposium on Discrete Algorithms (SODA), 2017.
Download Paper

Competitive analysis of the top-K ranking problem

Published in Proceedings of the Twenty-Eighth Annual ACM-SIAM Symposium on Discrete Algorithms, 2017

Journal version: IEEE Transactions on Information Theory, 2018

Recommended citation: Xi Chen, Sivakanth Gopi, Jieming Mao, Jon Schneider, "Competitive analysis of the top-K ranking problem." Proceedings of the Twenty-Eighth Annual ACM-SIAM Symposium on Discrete Algorithms, 2017.
Download Paper

2-server PIR with subpolynomial communication

Published in Proceedings of the forty-seventh annual ACM symposium on Theory of Computing (STOC), 2015

Winner of STOC best paper award.
Journal version: Invited article in Journal of the ACM, 2016.
Coverage: Bill Gasarch, Theorem of the year 2014 (Lance Fortnow)

Recommended citation: Zeev Dvir, Sivakanth Gopi, "2-server PIR with subpolynomial communication." Proceedings of the forty-seventh annual ACM symposium on Theory of Computing (STOC), 2015.
Download Paper

Synthesis from incompatible specifications

Published in Proceedings of the tenth ACM international conference on Embedded software, 2012

Recommended citation: Pavol {\v{C}}ern{\`y}, Sivakanth Gopi, Thomas Henzinger, Arjun Radhakrishna, Nishant Totla, "Synthesis from incompatible specifications." Proceedings of the tenth ACM international conference on Embedded software, 2012.
Download Paper

Patents


Privacy preserving user personalization using noisy ranking

Published in US Patent App. 18/301,943, 2024

US Patent App. 18/301,943

Recommended citation: Erik Anderson, Joseph PFEIFFER, Denis Charles, Aleksandr Rebrikov, John Mooring, Brandon Maslen, Davis Gilton, Sergey Yekhanin, Sivakanth Gopi, "Privacy preserving user personalization using noisy ranking." US Patent App. 18/301,943, 2024.

Noise generation for differential privacy

Published in US Patent 11,343,012, 2022

US Patent 11,343,012

Recommended citation: Anjaneya Malpani, Jagadeesh Huliyar, Xinyun Sun, Sreeram Nivarthi, Muthukrishnan Paramasivam, Dheepak Ramaswamy, Sriradha Selvaraj, Ananthatejas Raghavan, Sergey Yekhanin, Janardhan Kulkarni, Aleksey Ashikhmin, Sivakanth Gopi, Bingran Luo, "Noise generation for differential privacy." US Patent 11,343,012, 2022.