RealML@ICML2020: Workshop on Real World Experiment Design and Active Learning at ICML 2020 Messe Wien Exhibition Congress Center Vienna, Austria, July 17-18, 2020 |
Conference website | https://realworldml.github.io/ |
Submission link | https://easychair.org/conferences/?conf=realmlicml2020 |
Abstract registration deadline | June 22, 2020 |
Submission deadline | June 22, 2020 |
We would like to invite you to submit your work to the Workshop on Real World Experimental Design and Active Learning at ICML 2020, which will be held on July 17/18, 2020. Like ICML, this workshop will be held as a virtual event (due to COVID-19).
This workshop aims to bring together researchers from academia and industry to discuss major challenges, outline recent advances, and highlight future directions pertaining to novel and existing large-scale real-world experiment design and active learning problems. We aim to highlight new and emerging research opportunities for the ML community that arise from the evolving needs to make experiment design and active learning procedures that are theoretically and practically relevant for realistic applications.
Important Information
Website: realworldml.github.io
Workshop date: July 17/18, 2020
Location: Virtual workshop
Submission deadline: 22 June 2020, 11:59 PM (AoE time)
Submission Guidelines
We welcome submissions of 4-6 pages in JMLR Workshop and Proceedings format (excluding references). Submissions should be non-anonymous. All accepted papers will be presented as posters (recently published or under-review work is also welcome). There will be no archival proceedings, however, the accepted papers will be made available online on the workshop website.
Topics of Interest
Technical topics of interest include (but are not limited to):
- Large-scale and real-world experiment design (e.g. biological/molecular/drug design, physics, robotics, crowdsourcing, citizen science, algorithms, etc.)
- Efficient active learning and exploration
- High-dimensional, scalable Bayesian and bandit optimization (e.g. contextual, multi-task)
- Sample-efficient interactive learning, hypothesis and A\B testing
- Corrupted or indirect measurements, multi-fidelity experimentation
- Incorporating domain-knowledge such as physics
- Safety and robustness during experimentation and of resulting designs
Invited Speakers
- Shipra Agrawal (Columbia University)
- Anca Dragan (UC Berkeley)
- Jennifer Listgarten (UC Berkeley)
- José Miguel Hernández Lobato (University of Cambridge)
- Pietro Perona (Caltech)
- Tom Rainforth (University of Oxford)
- Aaditya Ramdas (Carnegie Mellon University)
- Dorsa Sadigh (Stanford University)
- Angela Schoellig (University of Toronto)
Organization
- Ilija Bogunovic (ETH Zurich)
- Willie Neiswanger (Carnegie Mellon University)
- Yisong Yue (Caltech)
Venue
Like ICML, this workshop will be held as a virtual event (due to COVID-19).
Contact
All questions about submissions should be emailed to ilijab@ethz.ch, willie@cs.cmu.edu, and/or yyue@caltech.edu