Schedule for: 24w5301 - Structured Machine Learning and Time–Stepping for Dynamical Systems

Beginning on Sunday, February 18 and ending Friday February 23, 2024

All times in Banff, Alberta time, MST (UTC-7).

Sunday, February 18
16:00 - 17:30 Check-in begins at 16:00 on Sunday and is open 24 hours (Front Desk - Professional Development Centre)
17:30 - 19:30 Dinner (Vistas Dining Room)
20:00 - 22:00 Informal gathering (Other (See Description))
Monday, February 19
07:00 - 08:45 Breakfast (Vistas Dining Room)
08:45 - 09:00 Introduction and Welcome by BIRS Staff (TCPL 201)
09:00 - 09:45 Emil Constantinescu: Subgrid-Scale Operators with Neural Ordinary Differential Equations (TCPL 201)
09:45 - 10:30 Takaharu Yaguchi: Numerical integrators for learning neural ordinary differential equation models (TCPL 201)
10:30 - 11:00 Coffee Break (TCPL Foyer)
11:00 - 11:45 Lisa Kreusser: Dynamical systems in deep generative modelling (TCPL 201)
11:55 - 13:20 Lunch (Vistas Dining Room)
13:30 - 14:15 Hongkun Zhang: Machine learning of conservation laws for dynamical systems (TCPL 201)
14:15 - 15:00 Christian Offen: Learning Lagrangian dynamics from data with UQ (TCPL 201)
15:00 - 15:30 Coffee Break (TCPL Foyer)
15:30 - 16:15 Brynjulf Owren: Stability of numerical methods set on Euclidean spaces and manifolds with applications to neural networks (TCPL 201)
16:15 - 17:00 Simone Brugiapaglia: Practical existence theorems for deep learning approximation in high dimensions (TCPL 201)
17:00 - 17:45 Free Discussion (TCPL Foyer)
17:55 - 19:30 Dinner (Vistas Dining Room)
Tuesday, February 20
07:00 - 08:45 Breakfast (Vistas Dining Room)
09:00 - 09:45 Davide Murari: Improving the robustness of Graph Neural Networks with coupled dynamical systems (TCPL 201)
09:45 - 10:30 Eldad Haber: Time dependent graph neural networks (TCPL 201)
10:30 - 11:00 Group Photo / Coffee Break (TCPL Foyer)
11:00 - 11:45 Melanie Weber: Representation Trade-Offs in Geometric Machine Learning (Online)
11:55 - 13:20 Lunch (Vistas Dining Room)
13:30 - 14:15 Geoffrey McGregor: Conservative Hamiltonian Monte Carlo (TCPL 201)
14:15 - 15:00 Wu Lin: (Lie-group) Structured Inverse-free Second-order Optimization for Large Neural Nets (TCPL 201)
15:00 - 15:30 Coffee Break (TCPL Foyer)
15:30 - 16:15 Molei Tao: Optimization and Sampling in Non-Euclidean Spaces (TCPL 201)
16:15 - 17:00 Melvin Leok: The Connections Between Discrete Geometric Mechanics, Information Geometry, Accelerated Optimization and Machine Learning (TCPL 201)
17:00 - 17:45 Free Discussion (TCPL Foyer)
17:55 - 19:30 Dinner (Vistas Dining Room)
Wednesday, February 21
07:00 - 08:45 Breakfast (Vistas Dining Room)
09:00 - 09:45 Elena Celledoni: Deep neural networks on diffeomorphism groups for optimal shape reparameterization (TCPL 201)
09:45 - 10:30 Giacomo Dimarco: Control and neural network uncertainty quantification for plasma simulation (TCPL 201)
10:30 - 11:00 Coffee Break (TCPL Foyer)
11:00 - 11:45 Bethany Lusch: Computationally Efficient Data-Driven Discovery and Linear Representation of Nonlinear Systems For Control (TCPL 201)
11:55 - 13:20 Lunch (Vistas Dining Room)
13:30 - 17:30 Free Afternoon (Banff National Park)
17:30 - 19:30 Dinner (Vistas Dining Room)
Thursday, February 22
07:00 - 08:45 Breakfast (Vistas Dining Room)
09:00 - 09:45 Chris Budd: Adaptivity and expressivity in neural network approximations (TCPL 201)
09:45 - 10:30 Yen-Hsi Tsai: Efficient gradient descent algorithms for learning from multiscale data (TCPL 201)
10:30 - 11:00 Coffee Break (TCPL Foyer)
11:00 - 11:45 Michael Graham: Data-driven modeling of complex chaotic dynamics on invariant manifolds (TCPL 201)
11:55 - 13:20 Lunch (Vistas Dining Room)
13:30 - 14:15 Seth Taylor: A spatiotemporal discretization for diffeomorphism approximation (TCPL 201)
14:15 - 15:00 James Jackaman: Limited area weather modelling: interpolating with neural networks (TCPL 201)
15:00 - 15:30 Coffee Break (TCPL Foyer)
15:30 - 16:15 Daisuke Furihata: A particle method based on Voronoi decomposition for the Cahn–Hilliard equation (TCPL 201)
16:15 - 17:00 David Ketcheson: Explicit time discretizations that preserve dissipative or conservative energy dynamics (TCPL 201)
17:00 - 17:45 Open Problems / Discussion (TCPL Foyer)
17:30 - 19:30 Dinner (Vistas Dining Room)
Friday, February 23
07:00 - 08:45 Breakfast (Vistas Dining Room)
09:00 - 09:45 Kyriakos Flouris: Geometry aware neural operators for hemodynamics (TCPL 201)
09:45 - 10:30 Yolanne Lee: Learning PDEs from image data using invariant features (TCPL 201)
10:30 - 11:00 Coffee Break (TCPL Foyer)
10:30 - 11:00 Checkout by 11AM (Front Desk - Professional Development Centre)
11:00 - 11:45 Juntao Huang: Hyperbolic machine learning moment closures for kinetic equations (Online)
11:55 - 13:20 Lunch (Vistas Dining Room)