3 papers
cs.LG2025
Quantifying constraint hierarchies in Bayesian PINNs via per-constraint Hessian decomposition
Filip Landgren
Bayesian physics-informed neural networks (B-PINNs) merge data with governing equations to solve differential equations under uncertainty. However, interpreting uncertainty and ove…
hep-th2025
Predictions with limited data: Bayesian (X)PINNs, entanglement surfaces and overconfidence
Filip Landgren, Marika Taylor
Solving differential equations from limited or noisy data remains a key challenge for physics-informed neural networks (PINNs), which are typically applied to already known and smo…
hep-th2024
A multiverse model in dS wedge holography
Sergio E. Aguilar-Gutierrez, Filip Landgren
We construct a multiverse model where empty AdS space is cut off by a pair of accelerated dS space universes, at a finite AdS boundary cutoff which we treat as a …