This page is for online registration only.

2nd Workshop on Learning Dynamical System (WLDS2)

Venue: Hybrid: Online and Open Space at the RIKEN Nihonbashi Office
Date and Time: All times in Japan Standard Time (JST)
November 25, 2026, 10:00-18:10
November 26, 2026, 10:00-18:10
November 27, 2026, 10:00-12:20
For further details and information on on-site participation, please visit the following workshop website.
https://wlds-2-workshop.ishikawa-isao-5s.chatgpt.site/

The event is organized by Mathematical Science Team, Dynamical Systems Learning Team, and High-Dimensional Structure Theory Team, RIKEN AIP Center and co-organized by:
JST CREST: Nonlinear, dissipative, and random dynamics based on deterministic governing equations
Principal investigator: Aiko Yakeno (Tohoku University)
Grant number: JPMJCR24Q6
JST ARiSE: AI for Mathematics and Physics
JST CREST: Innovation in Interdisciplinary Mathematical Research via Single-Cell Data Science
Principal investigator: Yusuke Imoto (Kyoto University)
Grant number: JPMJCR24Q1

Program

Day 1

November 25 · Wednesday

Topology and model reduction

10:00-10:40 Riccardo Muolo (RIKEN)
Title: Dynamics beyond nodes: from topology to synchronization patterns in higher-order networks

10:40-10:50 Coffee break

10:50-11:30 Ying Wang (Fudan University)
Title: Entropy and topological conditional entropy in dynamical systems

11:30-11:40 Coffee break

11:40-12:20 Koichiro Yawata (Hitachi, Ltd.)
Title: Data-driven reduction of rhythmic dynamics through phase autoencoder

12:20-14:00 Lunch

Dynamics of Learning

14:00-14:40 Bingze Lu (National Chung Cheng University)
Title: How numerical integrators shape learned dynamics in neural ODEs

14:40-14:50 Coffee break

14:50-15:30 Xuejin Zhang (Jilin University)
Title: From nonlinear dynamical systems to neural network training: dynamics tracking via polynomials of unitary operators

15:30-15:40 Coffee break

15:40-16:20 Guillaume Braun (RIKEN)
Title: Overfitting of spectral gradient descent: how matrix geometry shapes generalization and implicit bias

16:20-16:40 Coffee break

Numerical methods and applications

16:40-17:20 Axel Turnquist (Beijing Institute of Mathematical Sciences and Applications)
Title: Convergence theory for monotone finite-difference schemes solving prescribed Jacobian equations on unbounded subsets of ℝⁿ, with applications to freeform optics and economics

17:20-17:30 Coffee break

17:30-18:10 Rauan Kelesbekov (University of Alberta)
Title: Effects of large-amplitude periodic perturbations on boundary layer separation

Day 2

November 26 · Thursday

Dynamical modeling and score learning

10:00-10:40 Jiachen Yao (Online) (California Institute of Technology)
Title: Physics is the best teacher: consistency learning for time-invariant operators of chaotic dynamics

10:40-10:50 Coffee break

10:50-11:30 Yao Li (Online) (University of Massachusetts Amherst)
Title: A probabilistic score estimation using the Bismut–Elworthy–Li formula

11:30-11:40 Coffee break

11:40-12:20 He Ma (Fudan University)
Title: From dynamics learning to dynamics creation: neural transfer learning for complex dynamical systems

12:20-14:00 Lunch

Memory-based modeling of complex systems

14:00-14:40 Qunxi Zhu (Fudan University)
Title: Memory-driven AI modeling of complex systems: methods and applications

14:40-14:50 Coffee break

14:50-15:30 Wanfeng Lu (Fudan University)
Title: From incomplete observations to predictive dynamics: a Koopman–Mori–Zwanzig perspective

15:30-15:50 Coffee break

Distributional dynamics and operator learning

15:50-16:30 Maria Oprea (Institute of Science and Technology Austria)
Title: Learning dynamical systems using measure based metrics

16:30-16:40 Coffee break

16:40-17:20 Yutong Zhang (Fudan University)
Title: Distributional prediction of single-cell dynamics

17:20-17:30 Coffee break

17:30-18:10 Yuanchao Xu (Kyoto University)
Title: Learning Kolmogorov backward operators for spectral analysis and forecasting: a data-driven variational Galerkin framework

Day 3

November 27 · Friday

Climate dynamics and data assimilation

10:00-10:40 Claire Valva (Online) (California Institute of Technology)
Title: Analysis and forecasting of the tropical atmosphere with Koopman operators

10:40-10:50 Coffee break

10:50-11:30 Pin-Ying Wu (Kyoto University)
Title: Data-driven sensitivity analysis of atmospheric dynamics using ensembles

11:30-11:40 Coffee break

11:40-12:20 Kota Takeda (Nagoya University)
Title: Ensemble data assimilation in high-dimensional chaotic systems: exploiting low-dimensional structures