[CMU AI Seminar] March 22 at 12pm (Zoom) -- Chirag Gupta (CMU) -- Provably calibrating ML classifiers without distributional assumptions -- AI Seminar sponsored by Morgan Stanley

[Asher Trockman]

Dear all,

We look forward to seeing you *next Tuesday (3/22)* from *1**2:00-1:00 PM
(U.S. Eastern time)* for the next talk of our *CMU AI seminar*, sponsored
by Morgan Stanley <https://www.morganstanley.com/about-us/technology/>.

To learn more about the seminar series or see the future schedule, please
visit the seminar website <http://www.cs.cmu.edu/~aiseminar/>.

On 3/22, *Chirag Gupta *(CMU) will be giving a talk titled
*"**Provably calibrating
ML classifiers without distributional assumptions**"* to share his work on
new notions of calibration in the multiclass setting.

*Title*: Provably calibrating ML classifiers without distributional
assumptions

*Talk Abstract*: Most ML classifiers provide probability scores for the
different classes. What do these scores mean? Probabilistic classifiers are
said to be calibrated if the observed frequencies of labels match the
claimed/reported probabilities. While calibration in the binary
classification setting has been studied since the mid-1900s, there is less
clarity on the right notion of calibration for multiclass classification.
In this talk, I will present recent work where we investigate the
relationship between commonly considered notions of multiclass calibration
and the calibration algorithms used to achieve these notions. We will
discuss our proposed notion of top-label calibration, and the general
framework of multiclass-to-binary (M2B) calibration. We show that any M2B
notion of calibration can be provably achieved, no matter how the data is
distributed. I will present these calibration guarantees as well as
experimental results on calibrating deep learning models. Our proposed
algorithms beat existing algorithms in most situations. Code for this work
is available at https://github.com/aigen/df-posthoc-calibration.

*Speaker Bio*: Chirag Gupta is a fourth-year PhD student in the Machine
Learning Department at CMU, advised by Aaditya Ramdas. He works on
principled methods for uncertainty quantification in classification and
regression problems.

*Zoom Link*:
https://cmu.zoom.us/j/99510233317?pwd=ZGx4aExNZ1FNaGY4SHI3Qlh0YjNWUT09

Thanks,
Asher Trockman
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mailman.srv.cs.cmu.edu/pipermail/ai-seminar-announce/attachments/20220318/33e84a49/attachment.html>