Connectionists: Call for Talks and Demos: ICLR 2019 Debugging ML Workshop

[Sarah Tan]

------------------------------------------------
ICLR 2019 Workshop on Debugging ML Models
*Call for Talks and Demos for Debugging-in-Practice Track*
Monday May 6th, 2019. New Orleans
https://debug-ml-iclr2019.github.io/
------------------------------------------------

Machine learning (ML) models are increasingly being employed to make highly
consequential decisions. A key challenge is identifying and correcting
systematic patterns of mistakes made by ML models before deploying them in
the real world.

For this workshop’s *Debugging-in-Practice track*, we solicit work that
advances the understanding of issues related to *debugging ML models in
practice*. Submissions from industry practitioners are encouraged. Accepted
submissions will be presented as *talks or interactive demos. *An award
will be given to the best submission in this track.

Topics of interest include but are not limited to:
- *Success and failure stories* from deploying ML models in the real world
- *Software and hardware tools *for model debugging -- demos of tools are
welcome and highly encouraged.
- Understanding the *domain-specific nuances *of debugging ML models -
e.g., debugging ML models in healthcare, criminal justice, public policy,
education, and other social good applications.
- Best practices for *debugging large-scale ML systems in industry*

Important Dates
- Submission deadline: April 1, 2019, 11.59pm Anywhere on Earth (AoE) time
- Acceptance notification: April 12, 2019 (before ICLR registration
cancellation deadline)
- Workshop: Monday May 6th 09:00 AM – 06:00 PM @ Room R3

Submission Instructions
- Submission page: https://easychair.org/conferences/?conf=debugml19
- In EasyChair, you will be asked to select if you would like to present
your work, if accepted, as a talk (7-15 minutes) during a
Debugging-in-Practice session at the workshop, or as an interactive demo
during a Posters & Demos session, or both.
- Submit extended abstracts of 1 page (not including references, and an
optional appendix) using any template with minimum 11 point font and page
margins of at least 1 inch. See workshop website for more details.
- If you intend to present your work as a demo, we strongly encourage you
to provide screenshots of the demo in the optional appendix.
- Concurrent submission to other venues is allowed. Work already published
or made public in some form will also be considered.

*An award will be given to the best submission in this track. *Camera-ready
versions of extended abstracts will be uploaded to the conference website
(unless requested not to), but there will be no formal published
proceedings.

Please check the workshop website https://debug-ml-iclr2019.github.io/ for
updated information and email debugging.ml at gmail.com any questions.

Organizers:
Himabindu Lakkaraju <https://web.stanford.edu/~himalv/> (Harvard University)
Sarah Tan <https://shftan.github.io/> (Cornell University and UCSF)
Julius Adebayo <http://juliusadebayo.com/> (MIT)
Jacob Steinhardt <https://cs.stanford.edu/~jsteinhardt/> (Open Philanthropy
Project and OpenAI)
D. Sculley <https://www.eecs.tufts.edu/~dsculley/> (Google)
Rich Caruana <https://www.microsoft.com/en-us/research/people/rcaruana/>
(Microsoft Research)
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mailman.srv.cs.cmu.edu/pipermail/connectionists/attachments/20190312/a338814d/attachment.html>