ITF inflates curvature in switching AL-RNNs by conditioning on one regime path while marginal likelihood reduces curvature with a missing-information correction for plausible switches, and evidence fine-tuning can degrade dynamical QoIs despite better held-out evidence.
blend step
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Teacher Forcing as Generalized Bayes: Optimization Geometry Mismatch in Switching Surrogates for Chaotic Dynamics
ITF inflates curvature in switching AL-RNNs by conditioning on one regime path while marginal likelihood reduces curvature with a missing-information correction for plausible switches, and evidence fine-tuning can degrade dynamical QoIs despite better held-out evidence.