Fast-Mixing Markov Chains without Gradients

arXiv:2606.27564 · math.ST, stat.CO, stat.ML · Submitted 2026-06-25 · Read on arXiv

Robert Kutri, Robert Scheichl

math.ST, stat.CO, stat.ML

Submitted: 2026-06-25

Comments: preprint

Code: https://github.com/rkutri/styne

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Fidelity — 10× in this paper · explained in 2 episodes
• Accuracy — 5× in this paper · explained in 1 episode
• Hyperparameters — 4× in this paper · explained in 2 episodes
• Inverse Problem — 4× in this paper · explained in 2 episodes
• Trace — 4× in this paper · explained in 2 episodes
• Bayesian Inference — 2× in this paper · explained in 6 episodes
• Consistency — 2× in this paper · explained in 3 episodes
• Delayed Acceptance with Regularisation and Tempering — 2× in this paper
• Benchmark — 1× in this paper · explained in 2 episodes
• Calibration — 1× in this paper · explained in 9 episodes
• Core — 1× in this paper · explained in 2 episodes
• DeepONet — 1× in this paper · explained in 2 episodes
• Effective Sample Size (ESS) — 1× in this paper · explained in 2 episodes
• Langevin Dynamics — 1× in this paper · explained in 3 episodes
• Monte Carlo Sampling — 1× in this paper · explained in 2 episodes
• Multi-Level Delayed Acceptance — 1× in this paper
• Neural Operators — 1× in this paper · explained in 2 episodes
• Preconditioning — 1× in this paper · explained in 2 episodes
• Theoretical Guarantees — 1× in this paper · explained in 2 episodes
• Uncertainty Quantification — 1× in this paper · explained in 9 episodes
• Wasserstein Distance — 1× in this paper · explained in 6 episodes

Sources

• On the convergence of Hamiltonian Monte Carlo
• Multilevel Delayed Acceptance MCMC with an Adaptive Error Model in PyMC3
• Ergodicity of Approximate MCMC Chains with Applications to Large Data Sets
• Performance of Neural and Polynomial Operator Surrogates

Related papers

• Conformal Prediction for Dyadic Regression Under Complex Missingness
• Sharp Asymptotic Theory of Maximum Likelihood Estimation for Gaussian Processes with an RBF Kernel
• Bentkus-type asymptotic e-values
• High-Dimensional Asymptotics of Differentially Private PCA
• A proximal gradient algorithm for composite log-concave sampling
• KL Convergence Guarantees for Score diffusion models under minimal data assumptions