paper-with-me

홈 › Papers

Nonasymptotic analysis of Stochastic Gradient Hamiltonian Monte Carlo under local conditions for nonconvex optimization

2020-02-13 · Ömer Deniz Akyildiz, Sotirios Sabanis

We provide a nonasymptotic analysis of the convergence of the stochastic gradient Hamiltonian Monte Carlo (SGHMC) to a target measure in Wasserstein-2 distance without assuming log-concavity. Our analysis quantifies key theoretical properties of the SGHMC as a sampler under local conditions which significantly improves the findings of previous results. In particular, we prove that the Wasserstein-2 distance between the target and the law of the SGHMC is uniformly controlled by the step-size of the algorithm, therefore demonstrate that the SGHMC can provide high-precision results uniformly in the number of iterations. The analysis also allows us to obtain nonasymptotic bounds for nonconvex optimization problems under local conditions and implies that the SGHMC, when viewed as a nonconvex optimizer, converges to a global minimum with the best known rates. We apply our results to obtain nonasymptotic bounds for scalable Bayesian inference and nonasymptotic generalization bounds.

📄 PDF Abstract BibTeX arXiv:2002.05465

Code (0)

등록된 구현이 없습니다.

Tasks

Bayesian InferenceGeneralization Bounds

Similar Papers 제목 키워드 기반

Stochastic Gradient Hamiltonian Monte Carlo for Non-Convex Learning

2019-03-25 · Huy N. Chau, Miklos Rasonyi

Stochastic Gradient Hamiltonian Monte Carlo (SGHMC) is a momentum version of stochastic gradient descent with properly injected Gaussian noise to find a global minimum. In this paper, non-asymptotic convergence analysis …

Stochastic Gradient Hamiltonian Monte Carlo with Variance Reduction for Bayesian Inference

2018-03-29 · Zhize Li, Tianyi Zhang, Shuyu Cheng, Jun Zhu 외

Gradient-based Monte Carlo sampling algorithms, like Langevin dynamics and Hamiltonian Monte Carlo, are important methods for Bayesian inference. In large-scale settings, full-gradients are not affordable and thus stocha…

Bayesian Inference

Stochastic Gradient Hamiltonian Monte Carlo Methods with Recursive Variance Reduction

2019-12-01 · NeurIPS 2019 12 · Difan Zou, Pan Xu, Quanquan Gu

Stochastic Gradient Hamiltonian Monte Carlo (SGHMC) algorithms have received increasing attention in both theory and practice. In this paper, we propose a Stochastic Recursive Variance-Reduced gradient HMC (SRVR-HMC) al…

Non-asymptotic convergence analysis of the stochastic gradient Hamiltonian Monte Carlo algorithm with discontinuous stochastic gradient with applications to training of ReLU neural networks

2024-09-25 · Luxu Liang, Ariel Neufeld, Ying Zhang

In this paper, we provide a non-asymptotic analysis of the convergence of the stochastic gradient Hamiltonian Monte Carlo (SGHMC) algorithm to a target measure in Wasserstein-1 and Wasserstein-2 distance. Crucially, comp…

Stochastic Optimization

Relativistic Monte Carlo

2016-09-14 · Xiaoyu Lu, Valerio Perrone, Leonard Hasenclever, Yee Whye Teh 외

Hamiltonian Monte Carlo (HMC) is a popular Markov chain Monte Carlo (MCMC) algorithm that generates proposals for a Metropolis-Hastings algorithm by simulating the dynamics of a Hamiltonian system. However, HMC is sensit…