Oriel — AI & technology worth noticing, every day.

Preconditioned Implicit Midpoint Langevin Sampling for Non-Smooth Bayesian Imaging

Paper · https://arxiv.org/abs/2611.09980

arXiv:2611.09980v1 Announce Type: new Abstract: We introduce P-IMLA, a preconditioned implicit-midpoint Langevin sampler for high-dimensional log-concave targets with non-smooth regularization. The obstruction is that the large steps enabled by matrix preconditioning are precisely where preconditioned Euler-Maruyama inflates stationary variance. Implicit midpoint removes this surplus via a Cayley-transform identity, making P-IMLA Gaussian-exact at any step size. Beyond Gaussians, whitening transfers the sharp IMLA contraction rate to $\kappa_{\mathrm{eff}}$, and backward-error analysis gives drift-only rather than Euler-type diffusion bias under explicit smoothness assumptions. An $M$-norm Moreau envelope yields a proximal non-smooth variant with a three-term error budget. Controlled Gaussian and TV-regularized imaging experiments confirm the predicted separation: the unpreconditioned midpoint scheme retains long transients as $\kappa_f$ grows, whereas P-IMLA remains $\kappa_{\mathrm{eff}}$-governed and near variance-exact.

First seen by Oriel on .

No saved summary available.

Aliases

SourceExternal IDURL
arXiv AI Papersoai:arXiv.org:2611.09980v1https://arxiv.org/abs/2611.09980 Read discussion