Continuous Time Perspectives in Machine Learning

In machine learning, discrete time approaches such as gradient descent algorithms and discrete building layers for neural architectures have traditionally dominated. Recently, we have seen that by bridging these discrete systems with their continuous counterparts we can not only develop new insights but we can construct novel and competitive ML approaches. By leveraging time, we can tap into the centuries of research such as dynamical systems, numerical integration and differential equations, and continue enhancing what is possible in ML.The workshop aims to to disseminate knowledge about the use of continuous time methods in ML; to create a discussion forum and create a vibrant community around the topic; to provide a preview of what dynamical system methods might further bring to ML; to find the biggest hurdles in using continuous time systems in ML and steps to alleviate them; to showcase how continuous time methods can enable ML to have large impact in certain application domains, such as climate prediction and physical sciences.Recent work has shown that continuous time approaches can be useful in ML, but their applicability can be extended by increasing the visibility of these methods, fostering collaboration and an interdisciplinary approach to ensure their long-lasting impact. We thus encourage submissions with a varied set of topics: the intersection of machine learning and continuous-time methods; the incorporation of knowledge of continuous systems to analyse and improve on discrete approaches; the exploration of approaches from dynamical systems and related fields to machine learning; the software tools from the numerical analysis community.We have a diverse set of confirmed speakers and panellists with expertise in architectures, optimisation, RL, generative models, numerical analysis, gradient flows and climate. We hope this will foster an interdisciplinary and collaborative environment cohesive for the development of new research ideas.