arXiv Statistics ML
Spectral gap of Metropolis-within-Gibbs under log-concavity
Read the original on arXiv Statistics ML →The Flow has not summarised this story yet — read it at arXiv Statistics ML.
Related stories
arXiv Machine Learning
Sep 10
Smoothed Picard Hamiltonian Monte Carlo
arXiv:2609.06906v1 Announce Type: cross Abstract: We develop a new low-accuracy sampler, called \emph{smoothed Picard Hamiltonian Monte Carlo}, which combines Gaussian smoothing, Picard iteration, an...
arXiv Statistics ML
Aug 26
A Non-asymptotic Analysis for Learning and Applying a Preconditioner in MCMC
The paper presents a non‑asymptotic analysis of Markov chain Monte Carlo (MCMC) algorithms that learn and apply a preconditioner based on either the target covariance or the expected Hessian of the target potential. It compares the finite‑time computational costs of these preconditioned schemes with unpreconditioned counterparts, providing guarantees for algorithms such as the Unadjusted Langevin Algorithm (ULA) and the proximal sampler. The analysis relies on a contraction assumption in the Wasserstein‑2 distance to formalize approximate independence and bridge modern MCMC theory with classical effective sample size heuristics.
arXiv Machine Learning
Jun 29
Monte Carlo with kernel-based Gibbs measures: Guarantees for probabilistic herding
arXiv:2402. 11736v3 Announce Type: replace Abstract: Kernel herding belongs to a family of deterministic quadratures that seek to minimize the maximum mean discrepancy (MMD), that is, the worst-case integration error over a reproducing kernel Hilbert space (RKHS).
arXiv AI
Jun 10
Sample Where You Struggle: Sharpening Base Model Reasoning via Entropy-Guided Power Sampling
arXiv:2606. 09926v1 Announce Type: cross Abstract: Sampling from the sequence-level power distribution $p^\alpha$ elicits RL-level reasoning from base language models without any parameter updates, but the standard Metropolis--Hastings (MH), a Markov Chain Monte Carlo (MCMC) sampler, is both expensive and slow-mixing.
arXiv Machine Learning
Aug 4
Wasserstein mixing time of the unadjusted Langevin algorithm
arXiv:2608. 02430v1 Announce Type: cross Abstract: We provide new estimates in Wasserstein distance for the asymptotic bias of the unadjusted Langevin algorithm, in the classical setting of log-smooth strongly log-concave measures.
arXiv Machine Learning
Jun 3
Self-Certifying Transport MCMC via Dual Spectral-Gap Certificates
arXiv:2605. 30722v2 Announce Type: replace Abstract: We propose CerT-MCMC, a framework that equips learned-transport Markov chain Monte Carlo with automatic, rigorous convergence certificates.