Machine learning (ML) models are increasingly being employed to make highly consequential decisions pertaining to employment, bail, parole, and lending. While such models can learn from large amounts of data and are often very scalable, their applicability is limited by certain safety challenges. A key challenge is identifying and correcting systematic patterns of mistakes made by ML models before deploying them in the real world.

The goal of this workshop, held at the 2019 International Conference on Learning Representations (ICLR), is to bring together researchers and practitioners with different perspectives on debugging ML models. Topics of interest are listed below, although we also welcome submissions that do not directly fit into these topics.

Important Dates

If you are a student or postdoc, we encourage you to apply for ICLR’s volunteer and travel grants before their March 13 deadline. If you need a visa to travel to the US, consider submitting your paper before the submission deadline. Then contact us so that we can fast track reviewing of your paper.

Submission Instructions

Accepted papers will be presented as posters at the workshop. Additionally, some accepted papers will also be invited to present spotlight or oral talks at the workshop. Selected papers will be recognized with Best Research Paper, Best Applied Paper, Best Student Paper awards. Camera-ready versions of accepted papers will be uploaded to the conference website (unless requested not to), but there will be no formal published proceedings.

Please email debugging.ml@gmail.com with any questions.

Confirmed Speakers & Panelists

Tentative Schedule

Time Event
8:50 - 9:00 Introductory Remarks from Organizers
9:00 - 9:40 Invited talk 1 (30-40 mins talk including 5 mins questions)
9:40 - 10:00 Contributed oral talk
10:00 - 10:15 Break
10:15 - 10:55 Invited talk 2
10:55 - 11:10 3 spotlight contributed talks (5 mins each)
11.10 - 12.00 First poster session
12.00 - 1.15 Lunch
1.15 - 1.45 Opinion piece (Cynthia Rudin): Interpretability and debugging?
1.45 pm - 2.00 Floor discussion (for opinion piece)
2.00 pm - 2.40 Invited talk 3
2.40 pm - 2.55 Break
2.55 pm - 3.40 Panel (Different perspectives on debugging ML models)
3.40 pm - 4.00 Contributed oral talk
4.00 pm - 4.40 Invited talk 4
4.40 pm - 5.30 Second poster session