Fwd: [HCII Seminar] Rich Caruana - "Friends Don’t Let Friends Deploy Black-Box Models: The Importance of Intelligibility in Machine Learning"

[Artur Dubrawski]

A relevant talk by an old friend of the Auton Lab.

Artur


---------- Forwarded message ---------
From: Adam Perer <adamperer at cmu.edu>
Date: Mon, Oct 3, 2022 at 12:50 PM
Subject: [HCII Seminar] Rich Caruana - "Friends Don’t Let Friends Deploy
Black-Box Models: The Importance of Intelligibility in Machine Learning"
To: <ml-all at cs.cmu.edu>


Rich Caruana, a Senior Principal Researcher at Microsoft Research, will be
giving a virtual HCII seminar on Friday, entitled, " Friends Don’t Let
Friends Deploy Black-Box Models: The Importance of Intelligibility in
Machine Learning".

Details below:

*Topic:             HCII Fall Seminar Series*

*Time:              **Friday, October 7, 2022 - 1:30 PM Eastern Time (US
and Canada) – Virtual *



The next presentation of the FALL 2022 Seminar session will be
conducted on *Friday,
October 7, from 1:30 to 2:45 pm via the Zoom. *The featured speaker --
VIRTUALLY (REMOTELY) -- will be *Rich Caruana from Microsoft Research.
  *

*Join Zoom Meeting:*


https://cmu.zoom.us/j/98589029500?pwd=YzYrTkVUU1pvN1AwUXpkbU55SXpYZz09

Meeting ID: 985 8902 9500
Passcode: 916104

*Rich Caruana, **Senior Principal Researcher at Microsoft Research in
Redmond, WA*



*Pres**entation Title**:  *   Friends Don’t Let Friends Deploy Black-Box
Models: The Importance of Intelligibility in Machine Learning


*Abstract:   *

In machine learning, sometimes tradeoffs must be made between accuracy,
privacy and intelligibility: the most accurate models usually are not very
intelligible or private, and the most intelligible models usually are less
accurate.  This can limit the accuracy and privacy of models that can
safely be deployed in mission-critical applications such as healthcare
where being able to understand, validate, edit, and trust models is
important.  EBMs (Explainable Boosting Machines) are a recent learning
method based on generalized additive models (GAMs) that are as accurate as
full complexity models, more intelligible than linear models, and which can
be made differentially private with little loss in accuracy.  EBMs make it
easy to understand what a model has learned and to edit the model when it
learns inappropriate things.  In the talk, I’ll present multiple case
studies where EBMs discover surprising patterns in data that would have
made deploying black-box models risky.  I’ll describe how to train these
glassbox models with boosted trees, and with deep neural nets, and I’ll
briefly discuss how we’re using these models to uncover and mitigate bias
in models where fairness and transparency are important.


*Bio: *

Rich Caruana is a senior principal researcher at Microsoft Research. Before
joining Microsoft, Rich was on the faculty in the Computer Science
Department at Cornell University, at UCLA’s Medical School, and at CMU’s
Center for Learning and Discovery.  Rich’s Ph.D. is from Carnegie Mellon
University, where he worked with Tom Mitchell and Herb Simon.  His thesis
on Multi-Task Learning helped create interest in a new subfield of machine
learning called Transfer Learning.  Rich received an NSF CAREER Award in
2004 for Meta Clustering, best paper awards in 2005 (with Alex
Niculescu-Mizil), 2007 (with Daria Sorokina), and 2014 (with Todd Kulesza,
Saleema Amershi, Danyel Fisher, and Denis Charles), and co-chaired KDD in
2007.  His current research focus is on learning for medical decision
making, transparent modeling, and deep learning.


Adam Perer ( http://perer.org )
Data Interaction Group ( http://dig.cmu.edu )
Human-Computer Interaction Institute
Carnegie Mellon University
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mailman.srv.cs.cmu.edu/pipermail/autonlab-users/attachments/20221003/b0e2d2ba/attachment-0001.html>
-------------- next part --------------
A non-text attachment was scrubbed...
Name: ii_l8s75uqh1
Type: image/jpeg
Size: 244827 bytes
Desc: not available
URL: <http://mailman.srv.cs.cmu.edu/pipermail/autonlab-users/attachments/20221003/b0e2d2ba/attachment-0001.jpe>