About
Nidhi Hedge’s research focuses on a fundamental understanding of privacy and fairness in machine learning algorithms and systems, and the design of privacy-preserving and fair algorithms. She is interested in the generation of private synthetic data, privacy-preserving sequential sharing of data, the understanding of privacy in the context of sequential and non-independent data, and the understanding of potential tradeoffs between privacy and fairness.
Relevant Publications
- Wang, B., & Hegde, N. (2019). Privacy-preserving q-learning with functional noise in continuous spaces. In Advances in Neural Information Processing Systems (pp. 11327-11337).
- Cecchi, F., & Hegde, N. (2017). Adaptive active hypothesis testing under limited information. In Advances in Neural Information Processing Systems (pp. 4035-4043).
- Mukhopadhyay, A., Hegde, N., & Lelarge, M. (2019). Asymptotics of Replication and Matching in Large Caching Systems. IEEE/ACM Transactions on Networking, 27(4), 1657-1668.
- Banerjee, S., Hegde, N., & Massoulié, L. (2015). The price of privacy in untrusted recommender systems. IEEE Journal of Selected Topics in Signal Processing, 9(7), 1319-1331.
Support Us
CIFAR is a registered charitable organization supported by the governments of Canada, Alberta and Quebec, as well as foundations, individuals, corporations and Canadian and international partner organizations.