The Synergy of Scientific and Machine Learning Modeling Workshop (“SynS & ML”) is an interdisciplinary forum for researchers and practitioners interested in the challenges of combining scientific and machine-learning models. The goal of the workshop is to gather together machine learning researchers eager to include scientific models into their pipelines, domain experts working on augmenting their scientific models with machine learning, and researchers looking for opportunities to incorporate ML in widely-used scientific models.
The power of machine learning (ML), its ability to build models by leveraging real-world data is also a big limitation; the quality and quantity of training data bound the validity domain of ML models. On the other hand, expert models are designed from first principles or experiences and labelled scientific if validated on curated real-world data, often even harvested for this specific purpose, as advised by the scientific method since Galileo. Expert models only describe idealized versions of the world which may hinder their deployment for important tasks such as accurate forecasting or parameter inference. This workshop focuses on the combination of two modelling paradigms: scientific and ML modelling. Sometimes called hybrid learning or grey-box modelling, this combination should 1) unlock new applications for expert models, and 2) leverage the data compressed within scientific models to improve the quality of modern ML models. In this spirit, the workshop focuses on the symbiosis between these two complementary modelling approaches; it aims to be a “rendezvous” between the involved communities, spanning sub-fields of science, engineering and health, and encompassing ML, to allow them to present their respective problems and solutions and foster new collaborations. The workshop invites researchers to contribute to such topics; see Call for Papers and Call for Scientific Models for more details.
This workshop will be an in-person event (with some virtual components such as online talks and videos by authors) at ICML 2023.
Please check Accepted Contributions for poster session assignment. The assignment was updated on Thursday because the initial assignment did not consider the time slot preference we asked. Sorry for confusion.
|09:00–09:30||Talk: Two for One: Diffusion Models and Force Fields for Coarse-Grained Molecular Dynamics by Rianne van den Berg|
|09:30–10:00||Talk: The Domain Generalization Issue in Data-Based Dynamical Models by Patrick Gallinari|
|10:30–11:00||Talk: Climate modeling with AI: Hype or Reality? by Laure Zanna|
|11:00–12:00||Poster session AM (Poster Instruction; Session Assignment)|
|12:00–13:00||Lunch (on your own)|
|13:00–13:30||Talk: AI-Augmented Epidemiology for Covid-19 by Sercan Ö. Arık|
|13:30–14:00||Talk: Underspecification, Inductive Bias, and Hybrid Modeling by Andrew Miller|
|14:00–15:00||Contributed oral presentations|
|15:30–16:00||Best paper award presentations|
|16:00–17:00||Poster session PM (Poster Instruction; Session Assignment)|
Speakers & Panelists
Please contact the organizers at: firstname.lastname@example.org