3 papers
cs.LG2026
Forecasting Multiple Observables with SCROLL: Score-Trained Uncertainty for Stochastic Dynamics
Pavel Prochazka
Forecasting a stochastic dynamical system rarely means a single number: one wants several observables---future state, threshold event, regime label---each with its own likelihood.…
cs.LG2026
Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
Pavel Procházka, Pavel Prochazka
Posterior-seeking training need not produce the best predictive distribution in its family under model misspecification. For a last-layer weight belief, we locate the restriction r…
cs.LG2024
Convolutional Signal Propagation: A Simple Scalable Algorithm for Hypergraphs
Pavel Procházka, Marek Dědič, Lukáš Bajer
Last decade has seen the emergence of numerous methods for learning on graphs, particularly Graph Neural Networks (GNNs). These methods, however, are often not directly applicable…