Underdamped Langevin MCMC with third order convergence

Дата публикации: 17-08-2026 20:26:00

In this paper, we propose a new numerical method for the underdamped Langevin diffusion (ULD) and present a non-asymptotic analysis of its sampling error in the 2-Wasserstein distance when the $d$-dimensional target distribution $p(x)\propto e^{-f(x)}$ is strongly log-concave and has varying degrees of smoothness. Precisely, under the assumptions that the gradient and Hessian of $f$ are Lipschitz continuous, our algorithm achieves a 2-Wasserstein error of $\varepsilon$ in $\mathcal{O}\big(\sqrt{d}/\varepsilon\big)$ and $\mathcal{O}\big(\sqrt{d}/\sqrt{\varepsilon}\big)$ steps respectively. Therefore, our algorithm has a similar complexity as other popular Langevin MCMC algorithms under matching assumptions. However, if we additionally assume that the third derivative of $f$ is Lipschitz continuous, then our algorithm achieves a 2-Wasserstein error of $\varepsilon$ in $\mathcal{O}\big(\sqrt{d}/\varepsilon^{\frac{1}{3}}\big)$ steps. To the best of our knowledge, this is the first gradient-only method for ULD with third order convergence. To support our theory, we perform Bayesian logistic regression across a range of real-world datasets, where our algorithm achieves competitive performance compared to an existing underdamped Langevin MCMC algorithm and the popular No U-Turn Sampler (NUTS).

Схожие новости

#	Наименование новости	Тональность	Информативность	Дата публикации
1	Convergence of Noise-Free Sampling Algorithms with Regularized Wasserstein Proximals	0	8.02	17-08-2026
2	Accelerating Constrained Sampling: A Large Deviations Approach	0	7.94	17-08-2026
3	Mixing times of data-augmentation Gibbs samplers for high-dimensional probit regression	0	8.78	17-08-2026
4	Graph-based Clustering Revisited: A Relaxation of Kernel k-Means Perspective	0	10.94	17-08-2026
5	Deconvolution in unlinked linear models	0	4.62	17-08-2026
6	Minimax Optimal Convergence of Gradient Descent in Logistic Regression via Large and Adaptive Stepsizes	0	7.52	17-08-2026
7	Asymptotics of Stochastic Gradient Descent with Dropout Regularization in Linear Models	0	5.86	17-08-2026
8	Near-optimal Delta-convex Estimation of Lipschitz Functions	0	9.71	17-08-2026
9	Cheap Bootstrap for Fast Uncertainty Quantification of Stochastic Gradient Descent	0	6.38	17-08-2026
10	Statistical guarantees for denoising reflected diffusion models	0	5.3	17-08-2026

Классификация: . Схожих патентов: 0. Схожих новостей: 10. Тональность: 0. Информативность: 8.25. Источник: jmlr.org.