Search Mailing List Archives


Limit search to: Subject & Body Subject Author
Sort by: Reverse Sort
Limit to: All This Week Last Week This Month Last Month
Select Date Range     through    

[theory-seminar] "Approximating cross-validation: guarantees for model assessment and selection" – Ashia Wilson (Thu, 18-Mar @ 4:30pm)

Tavor Baharav tavorb at stanford.edu
Fri Mar 12 16:48:07 PST 2021


Approximating cross-validation: guarantees for model assessment and
selectionAshia Wilson – Professor, MIT

Thu, 18-Mar / 4:30pm / Zoom:
https://stanford.zoom.us/meeting/register/tJckfuCurzkvEtKKOBvDCrPv3McapgP6HygJ

*To avoid Zoom-bombing, we ask attendees to sign in via the above URL to
receive the Zoom meeting details by email.*
Abstract

Cross-validation (CV) is the de facto standard for selecting accurate
predictive models and assessing model performance. However, CV suffers from
a need to repeatedly refit a learning procedure on a large number of
training datasets. To reduce the computational burden, a number of works
have introduced approximate CV procedures that simultaneously reduce
runtime and provide model assessments comparable to CV when the prediction
problem is sufficiently smooth. An open question however is whether these
procedures are suitable for model selection. In this talk, I’ll describe
(i) broad conditions under which the model selection performance of
approximate CV nearly matches that of CV, (ii) examples of prediction
problems where approximate CV selection fails to mimic CV selection, and
(iii) an extension of these results and the approximate CV framework more
broadly to non-smooth prediction problems like L1-regularized empirical
risk minimization.
Bio

Ashia is an Assistant Professor in EECS at MIT. Her research focuses on the
methodological foundations and theory of various topics in machine
learning. She is interested in developing frameworks for algorithmic
assessment and providing rigorous guarantees for algorithmic performance.
She received her BA from Harvard University with a concentration in applied
mathematics and a minor in philosophy, and a PhD from UC Berkeley in
statistics. She most recently held a postdoctoral position in the machine
learning group at Microsoft Research, New England.

*This talk is hosted by the ISL Colloquium
<https://isl.stanford.edu/talks/>. To receive talk announcements, subscribe
to the mailing list isl-colloq at lists.stanford.edu
<https://mailman.stanford.edu/mailman/listinfo/isl-colloq>.*
------------------------------

Mailing list: https://mailman.stanford.edu/mailman/listinfo/isl-colloq
This talk: http://isl.stanford.edu/talks/talks/2021q1/ashia-wilson/
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mailman.stanford.edu/pipermail/theory-seminar/attachments/20210312/c12b64f1/attachment.html>


More information about the theory-seminar mailing list