Sivakanth Gopi

Senior Researcher, Microsoft Research

Joined

September 2020

Names

Sivakanth Gopi (Preferred)

Emails

****@microsoft.com (Confirmed)

Personal Links

Homepage

Google Scholar

DBLP

Career & Education History

Senior Researcher

Microsoft Research (microsoft.com)

2020 – Present

Postdoc

Microsoft Research (microsoft.com)

2018 – 2020

PhD student

Princeton University (princeton.edu)

2013 – 2018

Undergrad student

Indian Institute of Technology Bombay (iitb.ac.in)

2009 – 2013

Advisors, Relations & Conflicts

PhD Advisor

Zeev Dvir

2013 – 2018

Expertise

Coding Theory

Present

Complexity Theory

Present

Differential Privacy

Present

Publications

PE-SGD: Differentially Private Deep Learning via Evolution of Gradient Subspace for Text
Tianyuan Zou, Zinan Lin, Sivakanth Gopi, Yang Liu, Ya-Qin Zhang, Robert Sim, Xin Deng, Sergey Yekhanin
- ICLR 2026 Poster
- Readers: Everyone
DiscQuant: A Quantization Method for Neural Networks Inspired by Discrepancy Theory
Jerry Chee, Arturs Backurs, Rainie Heck, Li Zhang, Janardhan Kulkarni, Thomas Rothvoss, Sivakanth Gopi
- Submitted to ICLR 2025
- Readers: Everyone
Selective Pre-training for Private Fine-tuning
Da Yu, Sivakanth Gopi, Janardhan Kulkarni, Zinan Lin, Saurabh Naik, Tomasz Lukasz Religa, Jian Yin, Huishuai Zhang
- Accepted by TMLR
- Readers: Everyone
Differentially Private Synthetic Data via Foundation Model APIs 2: Text
Chulin Xie, Zinan Lin, Arturs Backurs, Sivakanth Gopi, Da Yu, Huseyin A Inan, Harsha Nori, Haotian Jiang, Huishuai Zhang, Yin Tat Lee, Bo Li, Sergey Yekhanin
- SeT LLM @ ICLR 2024
- Readers: Everyone
Differentially Private Synthetic Data via Foundation Model APIs 2: Text
Chulin Xie, Zinan Lin, Arturs Backurs, Sivakanth Gopi, Da Yu, Huseyin A Inan, Harsha Nori, Haotian Jiang, Huishuai Zhang, Yin Tat Lee, Bo Li, Sergey Yekhanin
- ICML 2024 Spotlight
- Readers: Everyone
Training Private and Efficient Language Models with Synthetic Data from LLMs
Da Yu, Arturs Backurs, Sivakanth Gopi, Huseyin Inan, Janardhan Kulkarni, Zinan Lin, Chulin Xie, Huishuai Zhang, Wanrong Zhang
- SoLaR Poster
- Readers: Everyone
Differentially Private Synthetic Data via Foundation Model APIs 1: Images
Zinan Lin, Sivakanth Gopi, Janardhan Kulkarni, Harsha Nori, Sergey Yekhanin
- SyntheticData4ML 2023 Oral
- Readers: Everyone
Differentially Private Synthetic Data via Foundation Model APIs 1: Images
Zinan Lin, Sivakanth Gopi, Janardhan Kulkarni, Harsha Nori, Sergey Yekhanin
- ICLR 2024 poster
- Readers: Everyone
Differentially Private Model Compression via Selective Pretraining
Janardhan Kulkarni, Da Yu, Sivakanth Gopi, Zinan Lin, Saurabh Naik, Tomasz Lukasz Religa, Jian Yin, Huishuai Zhang
- Submitted to ICLR 2024
- Readers: Everyone
Privacy-Preserving In-Context Learning with Differentially Private Few-Shot Generation
Xinyu Tang, Richard Shin, Huseyin A Inan, Andre Manoel, Fatemehsadat Mireshghallah, Zinan Lin, Sivakanth Gopi, Janardhan Kulkarni, Robert Sim
- ICLR 2024 poster
- Readers: Everyone

View all 15 publications

Co-Authors

View all 53 co-authors