
RM
Rostislav Makarov, Tal Peer, Danilo de Oliveira, Timo Gerkmann
· 1 min read
ResearcharXiv cs.LG
Livin' on a Prior: Likelihood Score Approximation for Inverse Problems
arXiv:2609.34446v1 Announce Type: new
Abstract: Generative models have found great success as data-driven methods of solving inverse problems. Two popular approaches work either by combining a pretrained generative prior with a known degradation model, or by training a conditional generative model directly from paired data. We target a setting that spans both regimes: unknown degradations can be learned from few paired examples, while known degradations can be learned from self-generated samples. We introduce Likelihood Score Approximation (LSA), a generative framework that keeps a pretrained unconditional model fixed and learns an observation-conditioned model that approximates the likelihood score from paired samples. Within a conditional stochastic-interpolant framework, LSA can be trained in either score or velocity coordinates, independently of the unconditional model's native parameterization, and supports both deterministic and stochastic sampling. We further show empirically that the prior model can be swapped post-training while keeping the same LSA model. Across speech and image inverse problems, LSA operates effectively even at roughly 0.01% of the full training dataset. On the ImageNet-256 benchmark it achieves competitive or better restoration quality than strong posterior-sampling baselines while requiring up to several orders of magnitude fewer network evaluations.
Original source
This story was published by arXiv cs.LG and written by Rostislav Makarov, Tal Peer, Danilo de Oliveira, Timo Gerkmann. SyncAI.news shows a preview; the complete article is on the publisher's site.
Read the full story on arxiv.org


