Differentially Private Model Selection via Stability Arguments and the Robustness of the Lasso

By Adam D. Smith. 2013

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

1. Wenlong Mou
2. Liwei Wang
3. Rui Hu
4. Zonghao Huang
5. Yuanxiong Guo
6. Thomas Steinke
7. Yanmin Gong
8. Eric Chan-Tin

Citations in the corpus

• Tight Lower Bounds for Differentially Private Selection (2017, background): “Selection problems appear in many natural statistical problems, including private multiple hypothesis testing [1], sparse linear regression [2], [3], finding frequent itemsets [4], and as subroutines in algorithms for answering exponentially many statistical queries [5], [6], [7], [8], [9], approxim”
• Collect at Once, Use Effectively: Making Non-interactive Locally Private Learning Possible (2017, methodology): “[26] and [32] considered the convergence of private LASSO estimator under RSC and incoherence assumptions.”
• DP-ADMM: ADMM-Based Distributed Learning With Differential Privacy (2018, background): “Thakurta and Smith [30] explore the stability of model selection problems, and propose two differentially private algorithms based on perturbation stability and subsampling stability respectively.”