paper-with-me

홈 › Papers

Random Coordinate Underdamped Langevin Monte Carlo

2020-10-22 · Zhiyan Ding, Qin Li, Jianfeng Lu, Stephen J. Wright

The Underdamped Langevin Monte Carlo (ULMC) is a popular Markov chain Monte Carlo sampling method. It requires the computation of the full gradient of the log-density at each iteration, an expensive operation if the dimension of the problem is high. We propose a sampling method called Random Coordinate ULMC (RC-ULMC), which selects a single coordinate at each iteration to be updated and leaves the other coordinates untouched. We investigate the computational complexity of RC-ULMC and compare it with the classical ULMC for strongly log-concave probability distributions. We show that RC-ULMC is always cheaper than the classical ULMC, with a significant cost reduction when the problem is highly skewed and high dimensional. Our complexity bound for RC-ULMC is also tight in terms of dimension dependence.

📄 PDF Abstract BibTeX arXiv:2010.11366

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Variance reduction for Random Coordinate Descent-Langevin Monte Carlo

2020-06-10 · NeurIPS 2020 12 · Zhiyan Ding, Qin Li

Sampling from a log-concave distribution function is one core problem that has wide applications in Bayesian statistics and machine learning. While most gradient free methods have slow convergence rate, the Langevin Mont…

Langevin Monte Carlo: random coordinate descent and variance reduction

2020-07-26 · Zhiyan Ding, Qin Li

Langevin Monte Carlo (LMC) is a popular Bayesian sampling method. For the log-concave distribution function, the method converges exponentially fast, up to a controllable discretization error. However, the method require…

Computational Efficiency

Dimension-Independent Convergence of Underdamped Langevin Monte Carlo in KL Divergence

2026-03-02 · Shiyuan Zhang, Qiwei Di, Xuheng Li, Quanquan Gu arxiv

Underdamped Langevin dynamics (ULD) is a widely-used sampler for Gibbs distributions $π\propto e^{-V}$, and is often empirically effective in high dimensions. However, existing non-asymptotic convergence guarantees for d…

Delocalization of bias in unadjusted Hamiltonian Monte Carlo and underdamped Langevin

2026-07-16 · Yifan Chen, Xiaoou Cheng, Jonathan Niles-Weed, Jonathan Weare arxiv

Unadjusted samplers such as unadjusted Hamiltonian Monte Carlo and underdamped Langevin are well-known to be biased. Metropolis--Hastings adjustment has been conventionally incorporated into Hamiltonian Monte Carlo to el…

Accelerating Approximate Thompson Sampling with Underdamped Langevin Monte Carlo

2024-01-22 · Haoyang Zheng, Wei Deng, Christian Moya, Guang Lin

Approximate Thompson sampling with Langevin Monte Carlo broadens its reach from Gaussian posterior sampling to encompass more general smooth posteriors. However, it still encounters scalability issues in high-dimensional…

Thompson Sampling