(Near) Dimension Independent Risk Bounds for Differentially Private Learning

  title={(Near) Dimension Independent Risk Bounds for Differentially Private Learning},
  author={Prateek Jain and Abhradeep Thakurta},
In this paper, we study the problem of differentially private risk minimization where the goal is to provide differentially private algorithms that have small excess risk. In particular we address the following open problem: Is it possible to design computationally efficient differentially private risk minimizers with excess risk bounds that do not explicitly depend on dimensionality (p) and do not require structural assumptions like restricted strong convexity? In this paper, we answer the… CONTINUE READING
Highly Cited
This paper has 46 citations. REVIEW CITATIONS


Publications referenced by this paper.
Showing 1-10 of 21 references

Differentially private convex optimization for empirical risk minimization and highdimensional regression

  • Thakurta, Abhradeep Guha
  • PhD Dissertation,
  • 2013

Differentially private kernel learning

  • Jain, Prateek, Thakurta, Abhradeep
  • In ICML,
  • 2013

Similar Papers

Loading similar papers…