Connectionists: [CfP] I (Still) Can’t Believe It’s Not Better! ICBINB at NeurIPS Workshop

[Francisco J. Rodríguez Ruiz]

*Call for Papers: I (Still) Can’t Believe It’s Not Better!A workshop for
“beautiful” ideas that should have worked*
*Workshop date:* 13th or 14th December 2021
*Location:* Virtual, at NeurIPS 2021
*Website:* https://i-cant-believe-its-not-better.github.io/neurips2021/
*Submission deadline:* September 17th 2021

Beautiful ideas have shaped scientific progress throughout history.
However, beautiful ideas are often overlooked in a research environment
that heavily emphasizes state-of-the-art (SOTA) results, where the worth of
scientific works is defined by their immediate utility.

We invite submissions to “I (Still) Can’t Believe It’s Not Better!”
(ICBINB) Workshop @ NeurIPS2021. ICBINB will explore gaps between the
“form” and “function” of ideas in ML and AI research. Do you have a
beautiful (“form”) idea which does not yet work (“function”)?

We welcome the submission of research papers and abstracts from the broader
ML community describing original work that has not been submitted or
currently under review, has not been previously published nor accepted for
publication elsewhere, in any other journal or conference. In particular,
this work may touch on one or more of the following aspects:
+ Unexpected negative results or anomalies: ideas that do not provide
expected results, yet authors are able to explain why, bringing an
interesting closed-form piece of knowledge to the community.
+ Papers that are “stuck” yet contain beautiful/elegant ideas. Authors
should argue why the idea is of interest, rigorously describe the analysis,
and include a self-critique.
+ Criticism of and alternatives to default or standard practices (e.g.,
current evaluation metrics).
+ Meta-research on the role of “beauty” or negative results in broader ML
research (including statistics, data science, AI, and application areas).

Submissions should be 4 pages long at most (not including references) and
submitted via OpenReview platform by September 17th 2021 (see our website
for the submission link). The Appendix can be unlimited, but note that
reviewers are only required to read the main text. Accepted authors will be
invited to participate in a poster session at the workshop. These
submissions are non-archival, however reviewers will nominate exemplar
papers for submission in PMLR.

This workshop evolves from last year ICBINB at NeurIPS 2020 workshop. This
year, we expand the scope to a broader ML community beyond probabilistic
ML, and will further unpack the concept of beauty of ideas during the
workshop.

*Confirmed invited speakers*: Tom Griffiths (Princeton University, USA),
Michaela Rosca (DeepMind, London), Robert Williamson (Tübingen University,
Germany), Cosma Shalizi (Carnegie Mellon University, USA), Tina Eliassi-Rad
(Northeastern University, USA).


-- 
Francisco J. R. Ruiz
Research Scientist
DeepMind
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mailman.srv.cs.cmu.edu/pipermail/connectionists/attachments/20210804/095483ed/attachment.html>