Pith. sign in

REVIEW 1 cited by

Stability and Generalization of Differentially Private Minimax Problems

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2204.04858 v2 pith:NHFYNG2Q submitted 2022-04-11 cs.LG cs.CR

classification cs.LGcs.CR
keywords minimaxprivacygeneralgeneralizationparadigmanalyzedifferentialdifferentially
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

In the field of machine learning, many problems can be formulated as the minimax problem, including reinforcement learning, generative adversarial networks, to just name a few. So the minimax problem has attracted a huge amount of attentions from researchers in recent decades. However, there is relatively little work on studying the privacy of the general minimax paradigm. In this paper, we focus on the privacy of the general minimax setting, combining differential privacy together with minimax optimization paradigm. Besides, via algorithmic stability theory, we theoretically analyze the high probability generalization performance of the differentially private minimax algorithm under the strongly-convex-strongly-concave condition. To the best of our knowledge, this is the first time to analyze the generalization performance of general minimax paradigm, taking differential privacy into account.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Enhancing Privacy in Decentralized Min-Max Optimization: A Differentially Private Approach

    cs.LG 2025-08 reject novelty 6.0 of 10

    DPMixSGD injects calibrated Gaussian noise into local gradient estimates to make decentralized nonconvex-strongly-concave min-max optimization differentially private, while claiming to preserve the STORM convergence rate.

Pith tools