University of Cambridge > Talks.cam > Peter Whittle Lecture > Algorithmic stability for regression and classification

  Browse A-Z

Log in

Googledetails Microsoftdetails

🔐 Log In

Information on

Subscribing to talksdetails Finding a talkdetails Adding a talkdetails Disseminating talksdetails Help and Documentationdetails

ℹ️ Information

Algorithmic stability for regression and classification

Download to your calendar using vCal

If you have a question about this talk, please contact HoD Secretary, DPMMS .

In a supervised learning setting, a model fitting algorithm is unstable if small perturbations to the input (the training data) can often lead to large perturbations in the output (say, predictions returned by the fitted model). Algorithmic stability is a desirable property with many important implications such as generalization and robustness, but testing the stability property empirically is known to be impossible in the setting of complex black-box models. In this work, we establish that bagging any black-box regression algorithm automatically ensures that stability holds, with no assumptions on the algorithm or the data. Furthermore, we construct a new framework for defining stability in the context of classification, and show that using bagging to estimate our uncertainty about the output label will again allow stability guarantees for any black-box model. This work is joint with Jake Soloff and Rebecca Willett.

A wine reception in the Central Core will follow this lecture

This talk is part of the Peter Whittle Lecture series.

This talk is included in these lists:

Note that ex-directory lists are not shown.

Other lists

Faculty of Education, 184 Hills Road, Cambridge, CB2 8PQ, GS5, Room TBC Palmerston Room, The Fisher Building, St John’s College Robinson College, Crausaz Wordsworth Building, Adams Road, Cambridge, UK

Other talks

Afternoon Break Title to follow Secrets of the Surface: The Mathematical Vision of Maryam Mirzakhani ( EDI Film Screening) Title to be confirmed Title to be confirmed Title to be confirmed
 

© 2006-2025 Talks.cam, University of Cambridge. Contact Us | Help and Documentation | Privacy and Publicity