Corpus ID: 232092592

Private Stochastic Convex Optimization: Optimal Rates in 𝓁1 Geometry

@article{Asi2021PrivateSC,
  title={Private Stochastic Convex Optimization: Optimal Rates in 𝓁1 Geometry},
  author={Hilal Asi and V. Feldman and T. Koren and Kunal Talwar},
  journal={ArXiv},
  year={2021},
  volume={abs/2103.01516}
}
Stochastic convex optimization over an l1-bounded domain is ubiquitous in machine learning applications such as LASSO but remains poorly understood when learning with differential privacy. We show that, up to logarithmic factors the optimal excess population loss of any (ε, δ)-differentially private optimizer is √ log(d)/n + √ d/εn. The upper bound is based on a new algorithm that combines the iterative localization approach of Feldman et al. [FKT20] with a new analysis of private regularized… Expand
2 Citations

Figures from this paper

Private Non-smooth Empirical Risk Minimization and Stochastic Convex Optimization in Subquadratic Steps
  • PDF

References

SHOWING 1-10 OF 27 REFERENCES
Private stochastic convex optimization: optimal rates in linear time
  • 28
  • PDF
Information Theory and Statistics. Lecture Notes for Statistics 311/EE 377
  • url: http://web.stanford.edu/class/stats311/lecture-notes.pdf
  • 2019
Private Stochastic Convex Optimization with Optimal Rates
  • 44
  • PDF
Introductory Lectures on Stochastic Convex Optimization
  • The Mathematics of Data. IAS/Park City Mathematics Series. American Mathematical Society,
  • 2018
Relatively Smooth Convex Optimization by First-Order Methods, and Applications
  • 132
  • PDF
Between Pure and Approximate Differential Privacy
  • 69
  • PDF
...
1
2
3
...