Over the next decade, the biggest generator of data is expected to be devices that sense and control the physical world.
The explosion of real-time data that is emerging from the physical world requires a rapprochement of areas such as machine learning, control theory, and optimization. While control theory has been firmly rooted in the tradition of model-based design, the availability and scale of data (both temporal and spatial) will require rethinking the foundations of our discipline. From a machine learning perspective, one of the main challenges going forward is to go beyond pattern recognition and address problems in data-driven control and optimization of dynamical processes. Our overall goal is to create a new community of people who think rigorously across the disciplines, ask new questions, and develop the foundations of this new scientific area. We are happy to welcome you to the University of Oxford for the 6th annual L4DC.
News and updates
L4DC 2024 will begin accepting submissions via EasyChair on 1 October 2023. The deadline for submissions is 1 December 2023. For further details see here.
Call for papers
A "call for papers flyer" (pdf) is available here.
We invite submissions of short papers addressing topics including:
Foundations of learning of dynamics models
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
Physical learning in dynamical and control systems applications in robotics, autonomy, biology, energy systems, 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.
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.
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.
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.