Stability is stable: connections between replicability, privacy, and adaptive generalization

DOI10.1145/3564246.3585246WikidataQ130957563 ScholiaQ130957563MaRDI QIDQ6499247

Jessica Sorrell, Toniann Pitassi, Marco Gaboardi, Max Hopkins, Russell Impagliazzo, Satchit Sivakumar, Mark Bun, Unnamed Author

Publication date: 8 May 2024

zbMATH Keywords

generalizationdifferential privacyreplicabilityalgorithmic stability

Mathematics Subject Classification ID

Theory of computing (68Qxx)

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• A finite sample distribution-free performance bound for local discrimination rules
• Geometric random graphs on circles
• Preserving Statistical Validity in Adaptive Data Analysis
• The reusable holdout: Preserving validity in adaptive data analysis
• Distribution-free performance bounds for potential function rules
• Fingerprinting Codes and the Price of Approximate Differential Privacy
• Make Up Your Mind: The Price of Online Queries in Differential Privacy
• Learners that Use Little Information
• 10.1162/153244302760200704
• Private PAC learning implies finite Littlestone dimension
• Information-Theoretic Lower Bounds for Distributed Function Computation
• Algorithmic stability for adaptive data analysis
• Theory of Cryptography
• Sample-efficient proper PAC learning with approximate differential privacy

This page was built for publication: Stability is stable: connections between replicability, privacy, and adaptive generalization