Welcome to the new version of CaltechAUTHORS. Login is currently restricted to library staff. If you notice any issues, please email coda@library.caltech.edu
Published June 26, 2019 | Submitted
Report Open

A necessary and sufficient stability notion for adaptive generalization

Abstract

We introduce a new notion of the stability of computations, which holds under post-processing and adaptive composition, and 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 notions.

Attached Files

Submitted - 1906.00930.pdf

Files

1906.00930.pdf
Files (334.9 kB)
Name Size Download all
md5:02fabb7f117cee2567030fdf7e9d2a67
334.9 kB Preview Download

Additional details

Created:
August 19, 2023
Modified:
October 20, 2023