[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]

Hi all,

The seminar today by Chirag Gupta is happening right now!

In case you are interested:
https://cmu.zoom.us/j/99510233317?pwd=ZGx4aExNZ1FNaGY4SHI3Qlh0YjNWUT09

Thanks,
Asher

On Fri, Mar 18, 2022 at 5:26 PM Asher Trockman <ashert at cs.cmu.edu> wrote:

> 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/20220322/f38974ca/attachment.html>