Differentially private empirical risk minimization for AUC maximization

Puyu Wang, Zhenhuan Yang, Yunwen Lei, Yiming Ying*, Hai Zhang

*Corresponding author for this work

Research output: Contribution to journalJournal articlepeer-review

9 Citations (Scopus)


Area under the ROC curve (AUC) is a widely used performance measure for imbalanced classification. Oftentimes, the ubiquitous imbalanced data such as financial records from fraud detection or genomic data from cancer diagnosis contains sensitive information, and therefore it is of practical and theoretical importance to develop privacy-preserving AUC maximization algorithms. In this paper, we propose differentially private empirical risk minimization (ERM) for AUC maximization, and systematically study their privacy and utility guarantees. In particular, we establish guarantees on the generalization (utility) performance of the proposed algorithms with fast rates. The technical novelty contains fast rates for the regularized ERM in AUC maximization, which is established using the peeling techniques for Rademacher averages [1] and properties of U-Statistics [2,3] to handle statistically non-independent pairs of examples in the objective function, and a new error decomposition to handle strongly smooth losses (e.g. least square loss). In addition, we revisit the private ERM with pointwise loss [4,5] and show optimal rates can be obtained using the uniform convergence approach.

Original languageEnglish
Pages (from-to)419-437
Number of pages19
Publication statusPublished - 21 Oct 2021

Scopus Subject Areas

  • Computer Science Applications
  • Cognitive Neuroscience
  • Artificial Intelligence

User-Defined Keywords

  • AUC maximization
  • Differential privacy
  • Empirical risk minimization
  • Imbalanced classification


Dive into the research topics of 'Differentially private empirical risk minimization for AUC maximization'. Together they form a unique fingerprint.

Cite this