Papers › Near-Optimal Approximations for Bayesian Inference in Function Space
Near-Optimal Approximations for Bayesian Inference in Function Space
Veit Wild, James Wu, Dino Sejdinovic, Jeremias Knoblauch
We propose a scalable inference algorithm for Bayes posteriors defined on a reproducing kernel Hilbert space (RKHS). Given a likelihood function and a Gaussian random element representing the prior, the corresponding Bayes posterior measure Π_B can be obtained as the stationary distribution of an RKHS-valued Langevin diffusion. We approximate the infinite-dimensional Langevin diffusion via a projection onto the first M components of the Kosambi-Karhunen-Lo\`eve expansion. Exploiting the thus obtained approximate posterior for these M components, we perform inference for Π_B by relying on the law of total probability and a sufficiency assumption. The resulting method scales as O(M³+JM²), where J is the number of samples produced from the posterior measure Π_B. Interestingly, the algorithm recovers the posterior arising from the sparse variational Gaussian process (SVGP) (see Titsias, 2009) as a special case, owed to the fact that the sufficiency assumption underlies both methods. However, whereas the SVGP is parametrically constrained to be a Gaussian process, our method is based on a non-parametric variational family 𝒫(ℝᴹ) consisting of all probability measures on ℝᴹ. As a result, our method is provably close to the optimal M-dimensional variational approximation of the Bayes posterior Π_B in 𝒫(ℝᴹ) for convex and Lipschitz continuous negative log likelihoods, and coincides with SVGP for the special case of a Gaussian error likelihood.
Code
Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.
Code Syntology ran Syntology
Not run by Syntology. Nothing on this page verifies that the listed code works.
Tasks
Results from the paper archive 2025-07-28
No leaderboard rows for this paper in the archive.
Methods
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections