Scholar
Ananda Theertha Suresh
Google Scholar ID: K6ef57QAAAAJ
Google Research, New York
Citations & Impact
Citations
28,480
H-index
37
i10-index
72
Publications
20
Co-authors
48
list available
Contact
No contact links provided.
Publications
Resume (English only)
Academic Achievements
- SpecTr: Fast Speculative Decoding via Optimal Transport, NeurIPS 2023
- Remember what you want to forget: Algorithms for machine unlearning, NeurIPS 2021
- On the Renyi Differential Privacy of the Shuffle Model, CCS 2021 (Best paper award)
- Optimal multiclass overfitting by sequence reconstruction from hamming queries, ALT 2020 (Best paper award)
- Three approaches for personalization with applications to federated learning, Manuscript
- Distributed mean estimation with limited communication, ICML 2017
- A unified maximum likelihood approach for optimal distribution property estimation, ICML 2017 (Best paper award honorable mention)
- Optimal prediction of the number of unseen species, PNAS 2016
- Competitive distribution estimation: Why is Good-Turing good, NeurIPS 2015 (Best paper award)
Research Experience
- Currently a research scientist at Google Research, New York. During his Ph.D., he worked on fundamental statistical problems such as distribution estimation and testing.
Education
- Ph.D. in Electrical and Computer Engineering from University of California, San Diego, advised by Alon Orlitsky; Bachelor's degree in Engineering Physics from Indian Institute of Technology, Madras.
Background
- Research interests: Federated learning, unlearning, privacy, and language models. Professional fields: Machine learning, information theory, and statistics.
