Organisers:
Tiangang Cui (University of Sydney)
Chris Drovandi (Queensland University of Technology)
Jana de Wiljes (Technische Universität Ilmenau)
Sahani Pathiraja (University of New South Wales)
Scott Sisson (University of New South Wales)

Program Description: One major goal of scientific machine learning is to combine complex data sets and physical constraints to build models capable of supporting decision-making in critical scientific applications, for example, subsurface energy, natural hazard forecasting and precision clinical therapy. At the heart of scientific machine learning often lies a sequential learning problem: one seeks “online” or real-time estimates from models based on sequentially observed data and time-varying physical constraints. The typically high dimensional nature of the system states, large volume of data and real-time nature of the estimation problem poses significant theoretical and algorithmic challenges, including but not limited to the curse of dimensionality. In addition, the time-varying nature of sequential problems often makes the stability of many estimation algorithms degenerate at a super-linear rate. The development of fast and scalable sequential learning methods with rigorous theoretical guarantees has recently drawn considerable attention in statistical learning and computational mathematics communities. This research program aims to bring together experts in scientific machine learning, statistics, and computational mathematics to discuss the latest developments in sequential learning and collaborate on topics that are instrumental to sequential learning tasks.

Program Structure: TBD

Registration:

• Deadline: TBD
• Registration is by invitation only. If you are interested to participate in this program, please contact one of the organisers with your CV and research background.
• Arrival date: 16 November 2025

ASSOCIATED EVENTS
MATRIX Wine and Cheese Afternoon 18 November 2025
On the first Tuesday of each program, MATRIX provides a pre-dinner wine and cheese afternoon. Produce is locally-sourced to showcase delicacies from the region.