Sergey Yekhanin

Principal Researcher, Microsoft Research, Microsoft

Joined

July 2019

Names

Sergey Yekhanin

Emails

****@microsoft.com (Confirmed)

****@gmail.com (Confirmed)

Personal Links

Homepage

Google Scholar

DBLP

Career & Education History

Principal Researcher

Microsoft Research, Microsoft (microsoft.com)

2008 – Present

Postdoc

Mathematics, Institue for Advanced Study, Princeton (ias.edu)

2007 – 2008

PhD student

EECS, Massachusetts Institute of Technology (mit.edu)

2003 – 2007

Undergrad student

Computer Science, Lomonosov Moscow State University (msu.ru)

1997 – 2002

Advisors, Relations & Conflicts

Postdoc Advisor

Avi Wigderson

2007 – 2008

PhD Advisor

Madhu Sudan

2003 – 2007

Expertise

Differential privacy

Present

Publications

Differentially Private Synthetic Data via APIs 4: Tabular Data
Toan Tran, Arturs Backurs, Zinan Lin, Victor Reis, Li Xiong, Sergey Yekhanin
- Submitted to ICLR 2026
- Readers: Everyone
Differentially Private Synthetic Data via APIs 3: Using Simulators Instead of Foundation Models
Zinan Lin, Tadas Baltrusaitis, Sergey Yekhanin
- Submitted to ICLR 2026
- Readers: Everyone
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
Struct-Bench: A Benchmark for Differentially Private Structured Text Generation
Shuaiqi Wang, Vikas Raunak, Arturs Backurs, Victor Reis, Pei Zhou, Sihao Chen, Longqi Yang, Zinan Lin, Sergey Yekhanin, Giulia Fanti
- NeurIPS 2025 Datasets and Benchmarks Track poster
- Readers: Everyone
Latent Zoning Network: A Unified Principle for Generative Modeling, Representation Learning, and Classification
Zinan Lin, Enshu Liu, Xuefei Ning, Junyi Zhu, Wenyu Wang, Sergey Yekhanin
- NeurIPS 2025 poster
- Readers: Everyone
Differentially Private Synthetic Data via APIs 3: Using Simulators Instead of Foundation Model
Zinan Lin, Tadas Baltrusaitis, Sergey Yekhanin
- ICLR 2025 Workshop Data Problems Poster
- Readers: Everyone
Differentially Private Synthetic Data via APIs 3: Using Simulators Instead of Foundation Model
Zinan Lin, Tadas Baltrusaitis, Sergey Yekhanin
- ICLR 2025 Workshop SynthData
- Readers: Everyone
Linear Combination of Saved Checkpoints Makes Consistency and Diffusion Models Better
Enshu Liu, Junyi Zhu, Zinan Lin, Xuefei Ning, Shuaiqi Wang, Matthew B. Blaschko, Sergey Yekhanin, Shengen Yan, Guohao Dai, Huazhong Yang, Yu Wang
- ICLR 2025 Poster
- 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

View all 15 publications

Co-Authors

View all 48 co-authors