Call for Papers

We invite submissions of short papers addressing topics including:

• Foundations of learning of dynamics models
• System identification
• Optimization for machine learning
• Data-driven optimization for dynamical systems
• Distributed learning over distributed systems
• Reinforcement learning for physical systems
• Safe reinforcement learning and safe adaptive control
• Statistical learning for dynamical and control systems
• Bridging model-based and learning-based dynamical and control systems
• Physics-constrained learning
• Physical learning in dynamical and control systems applications in robotics, autonomy, transportation systems, cognitive systems, neuroscience, etc.

While the conference is open to any topic on the interface between machine learning, control, optimization, and related areas, its primary goal is to address scientific and application challenges in real-time physical processes modeled by dynamical or control systems.

Submission Instructions

• Submissions are limited to 10 pages in PMLR format with unlimited allowance for references (Latex Style Sheet). Acknowledgements do not count towards the page limit. We updated the template on March 9, 2022 to include the proceedings volume number for the final submission.
• If the submitted paper includes an appendix, it should also be within the 10-page limit.
• In their submission, authors may point to a tech report if they wish, e.g. on arXiv or on a personal webpage. (For long proofs, extensive results, etc.)
• L4DC reviewing is single blind.
• We will begin accepting submissions via EasyChair (CfP Link, Submission Link) on October 20, 2021.
• The deadline for submissions is 5:00 PM EST on December 7, 2021
• Please contact the conference organizers at l4dc-organizers@lists.stanford.edu if you have any questions.

Dual Submissions

Submissions that are substantially similar to papers that have been previously published, accepted for publication, or submitted in parallel to other peer-reviewed conferences with proceedings or journals may not be submitted to L4DC.

Important Dates

• Paper submission deadline: November 30, 2021, 5:00 PM EST December 7, 2021, 5:00PM EST
• Author notification: March 1, 2022.
• Final Paper Upload Deadline: April 5, 2022, 5 PM EST. Authors will be directly contacted by e-mail regarding the submission procedure.
• Conference: June 23-24, 2022.

Publication

• Accepted papers will be published electronically in the Proceedings of Machine Learning Research (PMLR).

Presentation Instructions

• All accepted papers will be presented as posters at this conference. A selected set of papers deemed particularly exceptional by the program committee will be presented as oral talks.
• The allocated time for the oral presentations is 10 minutes for the presentation and 3 minutes for the questions.
• At least one of each paper’s authors should be present at the conference to present the work.

Poster Instructions

• The poster size is 20×30 inches (portrait mode).
• Authors should feel free to use any template for their poster presentations.
• Posters do not need to be submitted before the conference, but they need to be printed and brought to the conference for presentation.

Proceedings and Recordings

• Conference proceedings are available online on PMLR: https://proceedings.mlr.press/v168/

• Conference videos are available on L4DC Youtube Channel.
  • Keynote Talk: Stephen Boyd
  • Keynote Talk: Sarah Dean
  • Keynote Talk: Chuchu Fan
  • Keynote Talk: Monroe Kennedy III
  • Oral Presentations 1
  • Oral Presentations 2
  • Oral Presentations 3
  • Oral Presentations 4

Keynote Speakers

Program

All times are stated in Pacific Time (PT).

Click here to access the social program.

L4DC Awards

Best Paper Award Winner

Weiming Zhi, Tin Lai, Lionel Ott, and Fabio Ramos, “Diffeomorphic Transforms for Generalised Imitation Learning”

Best Paper Award Finalists

Haitong Ma, Changliu Liu, Shengbo Eben Li, Sifa Zheng, and Jianyu Chen, “Joint Synthesis of Safety Certificate and Safe Control Policy using Constrained Reinforcement Learning”

Samarth Sinha, Jiaming Song, Animesh Garg, and Stefano Ermon, “Experience Replay with Likelihood-free Importance Weights”

Organizers

General Chair

Local Chair

Editor-in-chief

Co-editor

Co-editor

Publications & Social Chair

Co-Chair

Awards Chair

Steering Committee

Program Committee

We are grateful to the reviewers for all their efforts in reviewing the papers contributed to L4DC2022. (Full list of reviewers)

Awards Committee

Attendance Information

Registration Website

Tickets to L4DC 2022 can be bought through Stanford Ticket Office: https://sto.stanfordtickets.org/l4dc/registration

Important Dates

• Author registration opens: March 9, 2022
  • Authors will be contacted via email for registration instructions.
• Public registration opens: April 10, 2022
• Early-bird registration deadline: May 1, 2022

Registration fees

All prices are in US Dollars.

Only degree-seeking students at a degree-awarding institution are eligible for student registration pricing. Students need to fill in their institutions, departments, and student ID numbers during registration.

Only Keynote Talks and Oral Presentations will be live-streamed. There will be no streaming for the poster sessions.

Logistics

Directions: Palo Alto Event Center, 4249 El Camino Real, Palo Alto, CA 94306

Parking: Free parking is available at the venue.

Food: Lunch, morning, and afternoon coffee will be available for the conference participants.

Accommodation: Accommodation options for L4DC participants can be found here.

Health and Safety

The health and safety of our conference attendees are the top priority of L4DC organizers. L4DC is planned as an in-person event with all oral presentations and keynote talks being live-streamed. We will have outdoor space available for breaks and socializing. Our full health and safety policy can be seen here.

Code of Conduct

At the L4DC conference, we aim to create a safe, welcoming, and positive environment that facilitates exchanging ideas and forming professional connections. We expect all participants to be respectful towards each other. The conference will not tolerate harassment, discrimination, or personal attacks. Participants must stop any problematic behavior immediately. If you have concerns about problematic behavior, please notify the L4DC organizers at l4dc-organizers@lists.stanford.edu. If you would like to notify the organizers anonymously, please use this form: https://forms.gle/MBY23Do5ryvLuFQCA 

It is important to note that problematic communication can occur even without an explicit intent to offend or harass. Hence, we ask that all participants be mindful of how their comments can be interpreted, and err on the side of caution during formal and informal interactions.

Building the L4DC Community:

L4DC is interdisciplinary, bringing together researchers from control, robotics, machine learning, and optimization. One of the goals of L4DC is to build strong ties between these disciplines and enable active collaboration. Please consider taking on the constructive role of contributing to the community, instead of taking on a critical role to pinpoint flaws and weaknesses in the works of others during the conference. Focusing on weak points could cause others to retreat back to places where they feel comfortable, and instead of interdisciplinary interaction, we could end up with separate sub-clusters of people only interacting within their own fields. So please help us create a positive tone so that it is easy for the participants to leave their comfort zones, gain new perspectives, and form new collaborations

Sponsors

Gold Sponsors

Silver Sponsors

Bronze Sponsors