Hybrid Monte Carlo

By A. D. Kennedy. 1988

Subfields: Probabilistic & Bayesian Methods

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Probabilistic & Bayesian Methods

Citations in the corpus

Auto-Encoding Variational Bayes (2013, neutral): “The AEVB and Wake-Sleep methods were compared to Monte Carlo EM (MCEM) with a Hybrid Monte Carlo (HMC) [DKPR87] sampler; details are in the appendix.”
Generalizing Hamiltonian Monte Carlo with Neural Networks (2017, positive): “For densities over continuous spaces, Hamiltonian Monte Carlo (HMC; Duane et al., 1987; Neal, 2011) introduces independent, auxiliary momentum variables, and computes a new state by integrating Hamiltonian dynamics.”
Composable Effects for Flexible and Accelerated Probabilistic Programming in NumPyro (2019, methodology): “The No-U-Turn Sampler (NUTS) [14] is an extension of the Hamiltonian Monte Carlo (HMC) algorithm [15, 16], which can efﬁciently sample from high-dimensional continuous probability distributions.”
Stochastic Gradient Hamiltonian Monte Carlo (2014, methodology): “…posterior distribution of θ given a set of observations D : where the potential energy function U is given by Hamiltonian (Hybrid) Monte Carlo (HMC) (Duane et al., 1987; Neal, 2010) provides a method for proposing samples of θ in a Metropolis-Hastings (MH) framework that efﬁciently explores the…”
Automatic differentiation in machine learning: a survey (2015, background): “When model parameters are continuous, the Hamiltonian—or, hybrid— Monte Carlo (HMC) algorithm provides improved convergence characteristics avoiding the slow exploration of random sampling, by simulating Hamiltonian dynamics through auxiliary “momentum variables” (Duane et al, 1987).”
Normalizing Flows for Probabilistic Modeling and Inference (2019, neutral): “One prominent example is Hamiltonian Monte Carlo (HMC), also known as Hybrid Monte Carlo (Duane et al., 1987; Neal, 2010).”
Learning Generative Models with Visual Attention (2013, methodology): “5) We can explore the gaze variables using Hamiltonian Monte Carlo (HMC) algorithm [27, 28].”
Stan: A Probabilistic Programming Language (2017, methodology): “RHMC with SoftAbs uses ﬁrst, second, and third order derivatives to adapt to the local curvature of the posterior.”
The Problem of Infra-marginality in Outcome Tests for Discrimination (2016, methodology): “Given the observed data, we estimate the posterior distribution of the search thresholds via Hamiltonian Monte Carlo (HMC) sampling (Neal, 1994; Duane et al., 1987), a form of Markov chain Monte Carlo sampling (Metropolis et al.”
Magnetic Hamiltonian Monte Carlo (2016, methodology): “We briefly review the Markov chain construction below; see (Neal, 2011) or (Duane et al., 1987) for a more detailed description.”
Gaussian Processes to Speed up Hybrid Monte Carlo for Expensive Bayesian Integrals (2003, methodology): “The new method proposed in this paper is an elaboration of the Hybrid Monte Carlo (HMC) method of Duane et al. (1987), using a Gaussian Process (GP) model to guide the search and avoid too many references to the target density function.”
Hamiltonian ABC (2015, background): “HABC builds upon the connections between Hamiltonian Monte Carlo with stochastic gradients and well-established gradient approximations based on a minimal number of forward simulations, even in high-dimensions.”
Shadow hybrid Monte Carlo: an efficient propagator in phase space of macromolecules (2004, methodology): “The HMC, introduced in [4], uses MD to generate a global MC move and then uses the Metropolis criterion to accept or reject the move.”