no code implementations • NAACL (TrustNLP) 2021 • Oluwaseyi Feyisetan, Shiva Kasiviswanathan
Ensuring strong theoretical privacy guarantees on text data is a challenging problem which is usually attained at the expense of utility.
1 code implementation • 8 Nov 2023 • Michaela Hardt, William R. Orchard, Patrick Blöbaum, Shiva Kasiviswanathan, Elke Kirschbaum
Although the machine learning and systems research communities have proposed various techniques to tackle this problem, there is currently a lack of standardized datasets for quantitative benchmarking.
no code implementations • 7 Feb 2019 • Shiyun Chen, Shiva Kasiviswanathan
In this paper, we consider the problem of controlling FDR in an online manner.
1 code implementation • 31 Jul 2018 • Yu-Xiang Wang, Borja Balle, Shiva Kasiviswanathan
We study the problem of subsampling in differential privacy (DP), a question that is the centerpiece behind many successful differentially private machine learning algorithms.
no code implementations • ICML 2018 • Tal Wagner, Sudipto Guha, Shiva Kasiviswanathan, Nina Mishra
We consider the problem of labeling points on a fast-moving data stream when only a small number of labeled examples are available.