Preprint
Aug 2026
Learned proposals in trans-dimensional inference are optimal at equilibrium, not during assembly
It is shown that the optimal proposal for the dimension-changing birth move is a different object in different phases of the run, and that a learned state-independent birth proposal is useless in one phase and optimal in the other.
A. Sasli, N. Karnesis, M. Karamanis et al.
· 0 citations