World's Best Scientists 2026 revealed!

D-Index & Metrics

Computer Science

D-Index
33
Citations
5288
World Ranking
12589
National Ranking
5102

Overview

Abhradeep Thakurta is a researcher affiliated with Google in the United States. Their work primarily centers on the field of computer science, with a significant focus on artificial intelligence. Their research portfolio spans 122 publications, with 108 dedicated to artificial intelligence, supported by contributions to related subfields such as statistics and probability, sociology and political science, computer networks and communications, and computational theory and mathematics.

The main topics in Thakurta's research include privacy-preserving technologies in data, stochastic gradient optimization techniques, adversarial robustness in machine learning, cryptography and data security, random matrices and applications, complexity and algorithms in graphs, and mobile crowdsensing and crowdsourcing.

Thakurta has contributed extensively to publications across a variety of venues. They have 55 publications in the arXiv repository, reflecting a strong presence in preprint dissemination. Other notable venues include Leibniz-Zentrum für Informatik (Schloss Dagstuhl), Harvard Dataverse, Journal of Artificial Intelligence Research, and the Proceedings of the AAAI Conference on Artificial Intelligence.

Several recent notable papers authored by or involving Thakurta are:

  • How to DP-fy ML: A Practical Guide to Machine Learning with Differential Privacy, 2023, Journal of Artificial Intelligence Research
  • Tempered Sigmoid Activations for Deep Learning with Differential Privacy, 2021, Proceedings of the AAAI Conference on Artificial Intelligence
  • Encode, Shuffle, Analyze Privacy Revisited: Formalizations and Empirical Evaluation, 2020, arXiv (Cornell University)
  • Tempered Sigmoid Activations for Deep Learning with Differential Privacy, 2020, arXiv (Cornell University)
  • Advancing Differential Privacy: Where We Are Now and Future Directions for Real-World Deployment, 2024, Harvard Data Science Review

Frequent co-authors collaborating with Thakurta include Arun Ganesh, Shuang Song, Thomas Steinke, Om Thakkar, and Steve Chien. These collaborations suggest an active research network and joint efforts in advancing topics related to differential privacy, machine learning, and data privacy.

Best Publications

  • Private Empirical Risk Minimization: Efficient Algorithms and Tight Error Bounds

    Raef Bassily;Adam Smith;Abhradeep Thakurta

  • Private Convex Empirical Risk Minimization and High-dimensional Regression

    Daniel Kifer;Adam Smith;Abhradeep Thakurta

  • GUPT: privacy preserving data analysis made easy

    Prashanth Mohan;Abhradeep Thakurta;Elaine Shi;Dawn Song

  • Discovering frequent patterns in sensitive data

    Raghav Bhaskar;Srivatsan Laxman;Adam Smith;Abhradeep Thakurta

  • Analyze gauss: optimal bounds for privacy-preserving principal component analysis

    Cynthia Dwork;Kunal Talwar;Abhradeep Thakurta;Li Zhang

  • Differentially Private Online Learning

    Prateek Jain;Pravesh Kothari;Abhradeep Thakurta

  • Amplification by Shuffling: From Local to Central Differential Privacy via Anonymity

    Úlfar Erlingsson;Vitaly Feldman;Ilya Mironov;Ananth Raghunathan

  • Amplification by shuffling: from local to central differential privacy via anonymity

    Úlfar Erlingsson;Vitaly Feldman;Ilya Mironov;Ananth Raghunathan

  • How to DP-fy ML: A Practical Guide to Machine Learning with Differential Privacy

    Unknown

  • Is Interaction Necessary for Distributed Private Learning

    Adam Smith;Abhradeep Thakurta;Jalaj Upadhyay

  • Differentially Private Feature Selection via Stability Arguments, and the Robustness of the Lasso

    Abhradeep Guha Thakurta;Adam Smith

  • Towards Practical Differentially Private Convex Optimization

    Roger Iyengar;Joseph P. Near;Dawn Song;Om Thakkar

  • Nearly-optimal private LASSO

    Kunal Talwar;Abhradeep Thakurta;Li Zhang

  • Near) Dimension Independent Risk Bounds for Differentially Private Learning

    Prateek Jain;Abhradeep Guha Thakurta

  • Tempered Sigmoid Activations for Deep Learning with Differential Privacy.

    Nicolas Papernot;Abhradeep Thakurta;Shuang Song;Steve Chien

  • Privacy Amplification by Iteration

    Vitaly Feldman;Ilya Mironov;Kunal Talwar;Abhradeep Thakurta

  • Differentially Private Learning with Kernels

    Prateek Jain;Abhradeep Thakurta

  • Noiseless database privacy

    Raghav Bhaskar;Abhishek Bhowmick;Vipul Goyal;Srivatsan Laxman

  • Practical Locally Private Heavy Hitters

    Raef Bassily;Kobbi Nissim;Uri Stemmer;Abhradeep Guha Thakurta

  • Tempered Sigmoid Activations for Deep Learning with Differential Privacy.

    Nicolas Papernot;Abhradeep Thakurta;Shuang Song;Steve Chien

  • Differentially Private Empirical Risk Minimization: Efficient Algorithms and Tight Error Bounds

    Raef Bassily;Adam Smith;Abhradeep Thakurta

  • Private Stochastic Convex Optimization with Optimal Rates

    Raef Bassily;Vitaly Feldman;Kunal Talwar;Abhradeep Guha Thakurta

  • (Nearly) Optimal Algorithms for Private Online Learning in Full-information and Bandit Settings

    Abhradeep Guha Thakurta;Adam Smith

  • Privacy Amplification by Iteration

    Vitaly Feldman;Ilya Mironov;Kunal Talwar;Abhradeep Thakurta

  • Analyze Gauss: optimal bounds for privacy-preserving PCA

    Cynthia Dwork;Kunal Talwar;Abhradeep Thakurta;Li Zhang

Frequent Co-Authors

Adam Smith
Adam Smith Boston University
Kunal Talwar
Kunal Talwar Apple (United States)
Prateek Jain
Prateek Jain Google (United States)
Ilya Mironov
Ilya Mironov Google (United States)
Vitaly Feldman
Vitaly Feldman Apple (United States)
Sanjam Garg
Sanjam Garg University of California, Berkeley
Somesh Jha
Somesh Jha University of Wisconsin–Madison
Li Zhang
Li Zhang Google (United States)
Nicholas Carlini
Nicholas Carlini Google (United States)

If you think any of the details on this page are incorrect, let us know.

Report an issue

We appreciate your kind effort to assist us to improve this page, it would be helpful providing us with as much detail as possible in the text box below:

Related Online Degrees & Career Pathways

Expanding your knowledge in computer science doesn’t have to mean years of study on campus. Today, students can choose from flexible online pathways to launch or advance a tech career. For those looking to boost credentials quickly, consider the quickest online masters degree programs, which let you earn a respected master’s in less time—sometimes in just one year.

If you’re uncertain which degree matches your career goals, explore the best masters degree to get. These programs are in high demand with employers and often provide higher earning potential post-graduation.

Not ready for a full bachelor’s or master’s? There are 1 year associate degree programs online that offer technical skills and job-ready training for quick entry into the workforce. And for students concerned about expenses, many affordable online colleges deliver quality education and support without a heavy financial burden, making online learning more accessible than ever before.

Best Scientists Citing Abhradeep Thakurta

Trending Scientists

Recently Published Articles