Algorithmic warm starts for Hamiltonian Monte Carlo

• URL: http://arxiv.org/abs/2603.22741v1
• Date: Tue, 24 Mar 2026 03:06:48 GMT
• Title: Algorithmic warm starts for Hamiltonian Monte Carlo
• Abstract summary: Hamiltonian Monte Carlo is the default algorithm across mainstream software packages.<n>Finding a warm start is therefore the computational bottleneck for HMC.<n>We prove that emphnon-Metropolized HMC generates a warm start in $tildeO(d1/4)$ iterations.
• Score: 14.517286437348034
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Generating samples from a continuous probability density is a central algorithmic problem across statistics, engineering, and the sciences. For high-dimensional settings, Hamiltonian Monte Carlo (HMC) is the default algorithm across mainstream software packages. However, despite the extensive line of work on HMC and its widespread empirical success, it remains unclear how many iterations of HMC are required as a function of the dimension $d$. On one hand, a variety of results show that Metropolized HMC converges in $O(d^{1/4})$ iterations from a warm start close to stationarity. On the other hand, Metropolized HMC is significantly slower without a warm start, e.g., requiring $Ω(d^{1/2})$ iterations even for simple target distributions such as isotropic Gaussians. Finding a warm start is therefore the computational bottleneck for HMC. We resolve this issue for the well-studied setting of sampling from a probability distribution satisfying strong log-concavity (or isoperimetry) and third-order derivative bounds. We prove that \emph{non-Metropolized} HMC generates a warm start in $\tilde{O}(d^{1/4})$ iterations, after which we can exploit the warm start using Metropolized HMC. Our final complexity of $\tilde{O}(d^{1/4})$ is the fastest algorithm for high-accuracy sampling under these assumptions, improving over the prior best of $\tilde{O}(d^{1/2})$. This closes the long line of work on the dimensional complexity of MHMC for such settings, and also provides a simple warm-start prescription for practical implementations.

Related papers

• High-Order Langevin Monte Carlo Algorithms [3.4106874887901437]
  Langevin algorithms are popular Markov chain Monte Carlo (MCMC) methods for large-scale sampling problems.<n>We propose $P$-th order Langevin Monte Carlo (LMC) algorithms based on the discretizations of $P$-th order Langevin dynamics.<n>We obtain Wasserstein convergence guarantees for sampling from distributions with log-concave and smooth densities.
  arXiv  Detail & Related papers  (2025-08-24T22:37:44Z)
• Efficient Sampling on Riemannian Manifolds via Langevin MCMC [51.825900634131486]
  We study the task efficiently sampling from a Gibbs distribution $d pi* = eh d vol_g$ over aian manifold $M$ via (geometric) Langevin MCMC. Our results apply to general settings where $pi*$ can be non exponential and $Mh$ can have negative Ricci curvature.
  arXiv  Detail & Related papers  (2024-02-15T22:59:14Z)
• Quantum Metropolis-Hastings algorithm with the target distribution calculated by quantum Monte Carlo integration [0.0]
  Quantum algorithms for MCMC have been proposed, yielding the quadratic speedup with respect to the spectral gap $Delta$ compered to classical counterparts. We consider not only state generation but also finding a credible interval for a parameter, a common task in Bayesian inference. In the proposed method for credible interval calculation, the number of queries to the quantum circuit to compute $ell$ scales on $Delta$, the required accuracy $epsilon$ and the standard deviation $sigma$ of $ell$ as $tildeO(sigma/epsilon
  arXiv  Detail & Related papers  (2023-03-10T01:05:16Z)
• Faster high-accuracy log-concave sampling via algorithmic warm starts [6.117084972237769]
  In practice, high-accuracy samplers such as the classical Metropolis-adjusted Langevin algorithm (MALA) remain the de facto gold standard. We improve the dimension dependence of this sampling problem to $tildeO(d1/2)$, whereas the previous best result for MALA was $tildeO(d)$. Our main technical contribution settles this problem by establishing the first $tildeO(d1/2)$ R'enyi mixing rates for the discretized underdamped Langevin diffusion.
  arXiv  Detail & Related papers  (2023-02-20T19:27:21Z)
• Gaussian process regression and conditional Karhunen-Lo\'{e}ve models for data assimilation in inverse problems [68.8204255655161]
  We present a model inversion algorithm, CKLEMAP, for data assimilation and parameter estimation in partial differential equation models. The CKLEMAP method provides better scalability compared to the standard MAP method.
  arXiv  Detail & Related papers  (2023-01-26T18:14:12Z)
• Hamiltonian Monte Carlo for efficient Gaussian sampling: long and random steps [0.0]
  Hamiltonian Monte Carlo (HMC) is a Markov chain algorithm for sampling from a high-dimensional distribution with density $e-f(x)$. We show that HMC can sample from a distribution that is $varepsilon$-close in total variation distance using $widetildeO(sqrtkappa d1/4 log(1/varepsilon)$ gradient queries.
  arXiv  Detail & Related papers  (2022-09-26T15:29:29Z)
• Mean-Square Analysis with An Application to Optimal Dimension Dependence of Langevin Monte Carlo [60.785586069299356]
  This work provides a general framework for the non-asymotic analysis of sampling error in 2-Wasserstein distance. Our theoretical analysis is further validated by numerical experiments.
  arXiv  Detail & Related papers  (2021-09-08T18:00:05Z)
• What Are Bayesian Neural Network Posteriors Really Like? [63.950151520585024]
  We show that Hamiltonian Monte Carlo can achieve significant performance gains over standard and deep ensembles. We also show that deep distributions are similarly close to HMC as standard SGLD, and closer than standard variational inference.
  arXiv  Detail & Related papers  (2021-04-29T15:38:46Z)
• Truncated Log-concave Sampling with Reflective Hamiltonian Monte Carlo [0.0]
  We introduce Reflective Hamiltonian Monte Carlo (ReHMC), an HMC-based algorithm, to sample from a log-concave distribution restricted to a convex polytope. We prove that, starting from a warm start, it mixes in $widetilde O(kappa d2 ell2 log (1 / varepsilon))$ steps for a well-rounded polytope. Experiments suggest that ReHMC outperfroms Hit-and-Run and Coordinate-Hit-and-Run regarding the time it needs to produce an independent sample
  arXiv  Detail & Related papers  (2021-02-25T18:34:45Z)
• A New Framework for Variance-Reduced Hamiltonian Monte Carlo [88.84622104944503]
  We propose a new framework of variance-reduced Hamiltonian Monte Carlo (HMC) methods for sampling from an $L$-smooth and $m$-strongly log-concave distribution. We show that the unbiased gradient estimators, including SAGA and SVRG, based HMC methods achieve highest gradient efficiency with small batch size. Experimental results on both synthetic and real-world benchmark data show that our new framework significantly outperforms the full gradient and gradient HMC approaches.
  arXiv  Detail & Related papers  (2021-02-09T02:44:24Z)
• Sample Complexity of Asynchronous Q-Learning: Sharper Analysis and Variance Reduction [63.41789556777387]
  Asynchronous Q-learning aims to learn the optimal action-value function (or Q-function) of a Markov decision process (MDP) We show that the number of samples needed to yield an entrywise $varepsilon$-accurate estimate of the Q-function is at most on the order of $frac1mu_min (1-gamma)5varepsilon2+ fract_mixmu_min (1-gamma)$ up to some logarithmic factor.
  arXiv  Detail & Related papers  (2020-06-04T17:51:00Z)
• Logsmooth Gradient Concentration and Tighter Runtimes for Metropolized Hamiltonian Monte Carlo [23.781520510778716]
  This is the first high-accuracy mixing time result for logconcave distributions using only first-order function information. We give evidence that dependence on $kappa$ is likely to be necessary standard Metropolized firstorder methods.
  arXiv  Detail & Related papers  (2020-02-10T22:44:50Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.