2 papers
cs.LG2026
On Geometry Regularization in Autoencoder Reduced-Order Models with Latent Neural ODE Dynamics
Mikhail Osipov
We investigate geometric regularization strategies for learned latent representations in encoder--decoder reduced-order models. In a fixed experimental setting for the advection--d…
cs.LG2025
Symmetry-Breaking Descent for Invariant Cost Functionals
Mikhail Osipov
We study the problem of reducing a task cost functional , not assumed continuous or differentiable, defined over Sobolev-class signals , i…