Om ThakkarGraduate Student
Department of Computer Science
Email : omthkkr "at" bu.edu
dblp Google Scholar LinkedIn
Security group, and the Theoretical Computer Science group, at the Department of Computer Science, Boston University. My research is in privacy-preserving data analysis, with a specific focus on differential privacy and its applications to machine learning, deep learning, and adaptive data analysis. I am very fortunate to be advised by Dr. Adam Smith.
I completed the first 3.5 years of my Ph.D. in the Department of Computer Science and Engineering at
- September'18: I will be a Visiting Graduate Student in the Data Privacy program at Simons, Berkeley during Spring'19.
- September'18: Our paper titled Model-Agnostic Private Learning has been accepted for an oral presentation at NeurIPS 2018.
- Summer'18: I worked with Úlfar Erlingsson on improving the utility of Differentially Private Stochastic Gradient Descent, while interning at Google Brain, Mountain View.
- May'18: Our paper titled Differentially Private Matrix Completion Revisited has been accepted for a long talk in ICML 2018.
- March'18: Our paper titled Towards Practical Differentially Private Convex Optimization has been accepted to appear in S&P 2019.
- Fall'17: I worked with Dr. Dawn Song on practical differentially private convex optimization, as a Visiting Student Researcher at UC Berkeley.
- Summer'17: I worked with Brendan McMahan on using adaptivity for differentially private federated learning without hyperparameter tuning, while interning at Google, Seattle.
- My most recent resume (last updated in December, 2018) can be found here.
- Building Tools for Controlling Overfitting in Adaptive Data Analysis. Joint work with Ryan Rogers, Aaron Roth, and Adam Smith.
- Towards Practical Differentially Private Convex Optimization. Abstract▼ Joint work with Roger Iyengar, Joseph P. Near, Dawn Song, Abhradeep Thakurta, and Lun Wang. To appear in the 40th IEEE Symposium on Security and Privacy (S&P 2019).
- Model-Agnostic Private Learning. Abstract▼ Joint work with Raef Bassily, and Abhradeep Thakurta. In the 32nd Conference on Neural Information Processing Systems (NeurIPS 2018). Accepted for an oral presentation.
- Differentially Private Matrix Completion Revisited. Abstract▼ Joint work with Prateek Jain, and Abhradeep Thakurta. In the 35th International Conference on Machine Learning (ICML 2018). Presented as a long talk.
- Max-Information, Differential Privacy, and Post-Selection Hypothesis Testing. Abstract▼ Joint work with Ryan Rogers, Aaron Roth, and Adam Smith. In the 57th Annual IEEE Symposium on Foundations of Computer Science (FOCS 2016).
- Summer 2018: Research Intern at Google Brain, Mountain View, CA. Mentor: Úlfar Erlingsson.
- Fall 2017: Visiting Student Researcher at University of California, Berkeley, CA. Host: Dr. Dawn Song.
- Summer 2017: Research Intern at Google, Seattle, WA. Mentors: Brendan McMahan, and Martin Pelikan.
- Summer 2016: Research Intern in the CoreOS: Machine Learning team at Apple, Cupertino, CA.
- Model-Agnostic Private Learning, on October 12, 2018 @ the 2018 Open AIR: Industry Open House, BU. (Poster)
- Building Tools for Controlling Overfitting in Adaptive Data Analysis, on July 7, 2018 @ the Adaptive Data Analysis workshop, Simons Institute, Berkeley.
- Towards Practical Differentially Private Convex Optimization, on March 5, 2018 @ the Privacy Tools Project meeting, Harvard.
- Differentially Private Matrix Completion Revisited
- on May 2, 2018 @ the Mathematical Foundations of Data Privacy workshop, BIRS. (Talk video)
- on January 26, 2018 @ the BU Data Science (BUDS) Day, Boston University. (Poster)
- on December 12, 2017 @ the Privacy Tools Data Sharing workshop, Harvard University. (Poster)
- on October 9, 2017 @ the Security Seminar, UC Berkeley.
- A brief introduction to Concentrated Differential Privacy, on April 14, 2017 @ CSE Theory Seminar, Penn State.
- Max-Information, Differential Privacy, and Post-selection Hypothesis Testing
- on April 24, 2017 @ INSR Industry Day, Penn State. (Poster)
- on December 2, 2016 @ SMAC Talks, Penn State.
- on November 7, 2016 @ CSE Theory Seminar, UCSD.
- on October 14, 2016 @ CSE Theory Seminar, Penn State.
- Max-Information and Differential Privacy, on May 5, 2016 @ CSE Theory Seminar, Penn State.
- The Stable Roommates Problem with Random Preferences, on April 10, 2015 @ CSE Theory Seminar, Penn State.
- The Multiplicative Weights Update Method and an Application to Solving Zero-Sum Games Approximately, on November 3, 2014 @ CSE Theory Seminar, Penn State.
- Teaching assistant:
- CMPSC 465 Data Structures and Algorithms, Spring 2017 @ Penn State.
- CMPSC 360 Discrete Mathematics for Computer Science, Spring 2015 @ Penn State.
- IT 114 Object Oriented Programming, Spring 2014 @ DA-IICT.
- IT 105 Introduction to Programming, Fall 2013 @ DA-IICT.
- Reviewer for T-IFS 2019, JMLR 2018.
- Reviewer for NIST's The Unlinkable Data Challenge: Advancing Methods in Differential Privacy.
- External reviewer for PETS (2017-2019), S&P (2017, 2019), CCS 2018, ICML 2018, STOC (2016, 2018), ACSAC 2017, FOCS 2017, WABI 2015.
- Received travel awards for NeurIPS 2018, ICML 2018, and FOCS 2014.
- Received a GSO Conference Travel Grant for Summer 2018.
- Report on Node-differentially Private Algorithms for Graph Statistics. It includes joint work with Ramesh Krishnan.