paper-with-me

Papers

Thermostat-assisted continuously-tempered Hamiltonian Monte Carlo for Bayesian learning

2017-11-30 · NeurIPS 2018 12 · Rui Luo, Jianhong Wang, Yaodong Yang, Zhanxing Zhu, Jun Wang

We propose a new sampling method, the thermostat-assisted continuously-tempered Hamiltonian Monte Carlo, for Bayesian learning on large datasets and multimodal distributions. It simulates the Nos\'e-Hoover dynamics of a continuously-tempered Hamiltonian system built on the distribution of interest. A significant advantage of this method is that it is not only able to efficiently draw representative i.i.d. samples when the distribution contains multiple isolated modes, but capable of adaptively neutralising the noise arising from mini-batches and maintaining accurate sampling. While the properties of this method have been studied using synthetic distributions, experiments on three real datasets also demonstrated the gain of performance over several strong baselines with various types of neural networks plunged in.

📄 PDF Abstract BibTeX arXiv:1711.11511

Code (1)

hsvgbkhgbv/TACTHMC 공식 구현 pytorch

Similar Papers 제목 키워드 기반

Sampling from high-dimensional, multimodal distributions using automatically tuned, tempered Hamiltonian Monte Carlo

2021-11-12 · Joonha Park

Hamiltonian Monte Carlo (HMC) is widely used for sampling from high-dimensional target distributions with probability density known up to proportionality. While HMC possesses favorable dimension scaling properties, it en…

Quantum-Inspired Hamiltonian Monte Carlo for Bayesian Sampling

2019-12-04 · Ziming Liu, Zheng Zhang

Hamiltonian Monte Carlo (HMC) is an efficient Bayesian sampling method that can make distant proposals in the parameter space by simulating a Hamiltonian dynamical system. Despite its popularity in machine learning and d…

BIG-bench Machine LearningDenoisingImage DenoisingNetwork Pruning

Parallel-tempered Stochastic Gradient Hamiltonian Monte Carlo for Approximate Multimodal Posterior Sampling

2018-12-04 · Rui Luo, Qiang Zhang, Yuanyuan Liu

We propose a new sampler that integrates the protocol of parallel tempering with the Nos\'e-Hoover (NH) dynamics. The proposed method can efficiently draw representative samples from complex posterior distributions with …

Tempered Sequential Monte Carlo for Trajectory and Policy Optimization with Differentiable Dynamics

2026-04-23 · Heng Yang arxiv

We propose a sampling-based framework for finite-horizon trajectory and policy optimization under differentiable dynamics by casting controller design as inference. Specifically, we minimize a KL-regularized expected tra…

Humble your Overconfident Networks: Unlearning Overfitting via Sequential Monte Carlo Tempered Deep Ensembles

2025-05-16 · Andrew Millard, Zheng Zhao, Joshua Murphy, Simon Maskell

Sequential Monte Carlo (SMC) methods offer a principled approach to Bayesian uncertainty quantification but are traditionally limited by the need for full-batch gradient evaluations. We introduce a scalable variant by in…

image-classificationImage ClassificationOut of Distribution (OOD) DetectionTransfer Learning+1