Birs- 24w5301: Structured Machine Learning and Time–Stepping for Dynamical Systems
-
Title: Dynamical systems in deep generative modelling
Speaker:
Link:
-
Title: Machine learning of conservation laws for dynamical systems
Speaker:
Link:
-
Title: Learning Lagrangian dynamics from data with UQ
Speaker:
Link:
-
Title: Stability of numerical methods set on Euclidean spaces and manifolds with applications to neural networks
Speaker:
Link:
-
Title: Practical existence theorems for deep learning approximation in high dimensions
Speaker:
Link:
-
Title: Improving the robustness of Graph Neural Networks with coupled dynamical systems
Speaker:
Link:
-
Title: Time dependent graph neural networks
Speaker:
Link:
-
Title: Conservative Hamiltonian Monte Carlo
Speaker:
Link:
-
Title: (Lie-group) Structured Inverse-free Second-order Optimization for Large Neural Nets
Speaker:
Link:
-
Title: Optimization and Sampling in Non-Euclidean Spaces
Speaker:
Link:
-
Title: The Connections Between Discrete Geometric Mechanics, Information Geometry, Accelerated Optimization and Machine Learning
Speaker:
Link:
-
Title: Deep neural networks on diffeomorphism groups for optimal shape reparameterization
Speaker:
Link:
-
Title: Control and neural network uncertainty quantification for plasma simulation
Speaker:
Link:
-
Title: Adaptivity and expressivity in neural network approximations
Speaker:
Link:
-
Title: Efficient gradient descent algorithms for learning from multiscale data
Speaker:
Link:
-
Title: Data-driven modeling of complex chaotic dynamics on invariant manifolds
Speaker:
Link:
-
Title: A spatiotemporal discretization for diffeomorphism approximation
Speaker:
Link:
-
Title: A particle method based on Voronoi decomposition for the Cahn–Hilliard equation
Speaker:
Link:
-
Title: Explicit time discretizations that preserve dissipative or conservative energy dynamics
Speaker:
Link:
-
Title: Geometry aware neural operators for hemodynamics
Speaker:
Link: