A necessary and sufficient stability notion for adaptive generalization

Katrina Ligett, Moshe Shenfeld

Research output: Contribution to journalConference articlepeer-review

6 Scopus citations

Abstract

We introduce a new notion of the stability of computations, which holds under post-processing and adaptive composition. We show that the notion is both necessary and sufficient to ensure generalization in the face of adaptivity, for any computations that respond to bounded-sensitivity linear queries while providing accuracy with respect to the data sample set. The stability notion is based on quantifying the effect of observing a computation's outputs on the posterior over the data sample elements. We show a separation between this stability notion and previously studied notion and observe that all differentially private algorithms also satisfy this notion.

Original languageAmerican English
JournalAdvances in Neural Information Processing Systems
Volume32
StatePublished - 2019
Event33rd Annual Conference on Neural Information Processing Systems, NeurIPS 2019 - Vancouver, Canada
Duration: 8 Dec 201914 Dec 2019

Bibliographical note

Publisher Copyright:
© 2019 Neural information processing systems foundation. All rights reserved.

Fingerprint

Dive into the research topics of 'A necessary and sufficient stability notion for adaptive generalization'. Together they form a unique fingerprint.

Cite this