Jul 2026
Bayesian Experimental Design via Score Matching
This work shows that the double intractability of the EIG can be isolated from the policy learning by first solving a score matching problem that is independent of the policy used, then using the learned score approximation to train the policy in a singly intractable manner.
Angus Phillips, Gavin Kerrigan, Tom Rainforth
· arXiv.org · 0 citations