Recognition: unknown
The No-U-Turn Sampler: Adaptively Setting Path Lengths in Hamiltonian Monte Carlo
read the original abstract
Hamiltonian Monte Carlo (HMC) is a Markov chain Monte Carlo (MCMC) algorithm that avoids the random walk behavior and sensitivity to correlated parameters that plague many MCMC methods by taking a series of steps informed by first-order gradient information. These features allow it to converge to high-dimensional target distributions much more quickly than simpler methods such as random walk Metropolis or Gibbs sampling. However, HMC's performance is highly sensitive to two user-specified parameters: a step size {\epsilon} and a desired number of steps L. In particular, if L is too small then the algorithm exhibits undesirable random walk behavior, while if L is too large the algorithm wastes computation. We introduce the No-U-Turn Sampler (NUTS), an extension to HMC that eliminates the need to set a number of steps L. NUTS uses a recursive algorithm to build a set of likely candidate points that spans a wide swath of the target distribution, stopping automatically when it starts to double back and retrace its steps. Empirically, NUTS perform at least as efficiently as and sometimes more efficiently than a well tuned standard HMC method, without requiring user intervention or costly tuning runs. We also derive a method for adapting the step size parameter {\epsilon} on the fly based on primal-dual averaging. NUTS can thus be used with no hand-tuning at all. NUTS is also suitable for applications such as BUGS-style automatic inference engines that require efficient "turnkey" sampling algorithms.
This paper has not been read by Pith yet.
Forward citations
Cited by 7 Pith papers
-
Bayesian Doppler Imaging: Simultaneous Inference of Surface Maps and Geometric Parameters
A fully Bayesian pixel-based Doppler imaging framework uses Gaussian Process priors and Hamiltonian Monte Carlo to simultaneously infer surface maps and geometric parameters from spectral data.
-
High-dimensional inference for the $\gamma$-ray sky with differentiable programming
A differentiable forward model and likelihood enable probabilistic inference over many spatial morphologies for the Galactic Center gamma-ray Excess using variational methods on GPUs.
-
A renormalization-group inspired lattice-based framework for piecewise generalized linear models
RG-inspired lattice models for piecewise GLMs provide explicit interpretable partitions and a replica-analysis-derived scaling law for regularization that allows increasing complexity without expected rise in generali...
-
Tokenised Flow Matching for Hierarchical Simulation Based Inference
TFMPE combines likelihood factorisation with tokenised flow matching to enable efficient hierarchical SBI from single-site simulations, producing well-calibrated posteriors at lower computational cost on a new benchma...
-
QCD-factorization amplitudes from flavour symmetries: beyond the $SU(3)$ symmetric case
A data-driven SU(3)-breaking analysis of B to PP decays yields QCD-factorization amplitudes that resemble dynamical predictions and require no enhanced annihilation terms.
-
Bathymetry Reconstruction by Bayesian Inference
Bayesian inference reconstructs bathymetry from point water height measurements, improving NRMSE over adjoint optimization on real wave flume data while quantifying uncertainty.
-
Determining the Host Stars of Planets in Binary Star Systems with Asterodensity Profiling: Investigating the Canonical Radius Gap
Probabilistic host-star assignments via asterodensity profiling suggest the exoplanet radius gap is less empty in binary systems once possible circumsecondary planets are included.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.