Research
On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

168,695 papers · 148 categories

Trend · papers per month

7152229 · May 202619922001200920172026
48 results for NUTS sampler

This paper compares two NUTS variants and analyzes their convergence and mixing times.

problem Theoretical comparison and convergence guarantees of NUTS variants.
method Deriving necessary and sufficient conditions for geometric ergodicity, and analyzing mixing times.
result NUTS-mul and NUTS-BPS have nearly identical qualitative behavior but differ quantitatively in convergence rates.

NUTS mixing time scales as d^(1/4) for Gaussian distributions.

problem Improving the efficiency of the No-U-Turn Sampler (NUTS) for Gaussian distributions.
method Coupling argument leveraging geometric structure of Gaussian concentration, uniformity analysis of NUTS transitions.
result The mixing time of NUTS scales as d^(1/4) for Gaussian distributions, up to logarithmic factors.

This paper analyzes the convergence of dynamic HMC and NUTS methods.

problem Theoretical understanding of dynamic HMC and NUTS convergence.
method General class of MCMC algorithms, NUTS as a particular case, geometric ergodicity, irreducibility.
result NUTS is geometrically ergodic under certain conditions and ergodic without bounded stepsize.

WALNUTS improves sampling efficiency and robustness for multi-scale distributions.

problem Adapting leapfrog step size for multi-scale posterior distributions.
method Adapts leapfrog step size at fixed intervals of simulated time, selecting the largest step size to keep energy error below a threshold.
result Substantial improvements in sampling efficiency and robustness compared to standard NUTS.

L-HNNs improve Bayesian inference efficiency by reducing gradient computation.

problem Efficient Bayesian inference with minimal gradient computation.
method Integrating L-HNNs into NUTS with online error monitoring.
result L-HNNs in NUTS outperform NUTS in complex posterior densities.

L-HNNs improve Bayesian inference by reducing gradient requirements and improving ESS.

problem Efficient Bayesian inference with complex target densities.
method Latent Hamiltonian Neural Networks (L-HNNs) with NUTS, incorporating online error monitoring.
result L-HNNs in NUTS with online error monitoring required 1--2 orders of magnitude fewer numerical gradients and improved ESS by an order of magnitude.

We explore a general framework in Markov chain Monte Carlo (MCMC) sampling where sequential proposals are tried as a candidate for the next state of the Markov chain. This sequential-proposal framework can be applied to various existing MCMC methods, including Metropolis-Hastings algorithms using random proposals and m…

2019-07-15abs ↗pdf ↗

Improved particle filters for estimating model parameters using differentiable resampling.

problem Inability to differentiate sampling and resampling steps in particle filters.
method Extended reparameterisation trick to include stochastic input, enabling differentiation. Used p-MCMC and NUTS for parameter estimation.
result NUTS improves mixing of Markov chain and produces more accurate results in less time.

We describe a simple, low-level approach for embedding probabilistic programming in a deep learning ecosystem. In particular, we distill probabilistic programming down to a single abstraction---the random variable. Our lightweight implementation in TensorFlow enables numerous applications: a model-parallel variational …

2018-11-05abs ↗pdf ↗

Markov chain Monte Carlo (MCMC) methods are widely used in machine learning. One of the major problems with MCMC is the question of how to design chains that mix fast over the whole state space; in particular, how to select the parameters of an MCMC algorithm. Here we take a different approach and, similarly to paralle…

2018-06-11abs ↗pdf ↗

Novel framework for efficient Gaussian process models with monotonicity constraints.

problem Improving predictive accuracy and reducing uncertainty in high-dimensional problems with monotonicity constraints.
method Virtual point-based framework using regularized linear randomize-then-optimize (RLRTO) and No U-Turn Sampler (NUTS) for efficient sampling.
result Significant improvements in computational efficiency with the RLRTO method and NUTS enhancements.

Latent-IMH improves Bayesian inference for expensive operators.

problem Efficient sampling from posterior distributions in inverse problems with computationally expensive operators.
method Metropolis-Hastings independence sampler using approximate and exact operators.
result Latent-IMH outperforms existing methods in computational efficiency.

We propose a construction of Skyrme fields from holonomy of the spin connection of gravitational instantons. The procedure is implemented for Atiyah-Hitchin and Taub-NUT instantons. The skyrmion resulting from the Taub-NUT is given explicitly on the space of orbits of a left translation inside the whole isometry group.…

2012-05-31abs ↗pdf ↗

The paper explores Kähler structures of Taub-NUT and Kerr spaces.

problem Understanding Kähler properties of gravitational instantons and black holes.
method Analyzing Euclidean Taub-NUT and Kerr metrics using alternative coframes and conformal scaling.
result Euclidean Taub-NUT and Kerr metrics exhibit hyper-Kähler and globally conformally Kähler properties, respectively.

Instantons on multi-Taub-NUT spaces are mapped to bow representations.

problem Mapping instantons to bow representations for multi-Taub-NUT spaces.
method Proving gauge equivalence classes correspondence and isometry of moduli spaces.
result Instantons on multi-Taub-NUT spaces are isometric to bow representations.

We study the one-parameter family of twisted Kahler Taub-NUT metrics (discovered by Donaldson), along with two exceptional Taub-NUT-like instantons, and understand them to the extend that should be sufficient for blow-up and gluing arguments. In particular we parametrize their geodesics from the origin, determine curva…

2016-02-19abs ↗pdf ↗

Gravitational instantons are constructed as superpositions of Atiyah-Hitchin and Taub-NUT geometries.

problem Constructing gravitational instantons from Atiyah-Hitchin and Taub-NUT geometries.
method A gluing construction that captures the superposition of moduli spaces of centred SU(2) monopoles and Taub-NUT manifolds.
result Gravitational instantons are explicitly shown to be superpositions of Atiyah-Hitchin and Taub-NUT geometries.

Study on asymptotic behavior of Taub-NUT type solitons and construction of new ALF Calabi-Yau metrics.

problem Asymptotic behavior of steady gradient Kähler-Ricci solitons of Taub-NUT type.
method Determination of asymptotic cone, special case analysis, and construction of new metrics using Tian-Yau-Hein method.
result Construction of new ALF Calabi-Yau metrics on quotients of the Taub-NUT type soliton.

We present a construction of self-dual Yang-Mills connections on the Taub-NUT space. We illustrate it by finding explicit expressions for all SU(2) instantons of instanton number one and generic monodromy at infinity.

2009-02-27abs ↗pdf ↗

We introduce a generalization of Taub-NUT deformations for large families of hyper-Kaehler quotients including toric hyper-Kaehler manifolds and quiver varieties, and apply them to the case of the Hilbert schemes of k points on C^2.

2013-01-23abs ↗pdf ↗

This work aims mainly to present a project of research about the identification of the determinants that affect the mobility of labor. The empirical part of the work will be performed for the NUTS II and NUTS III of Portugal, from 1996 to 2002 and for 1991 and 2001, respectively (given the availability of statistical d…

2011-10-25abs ↗pdf ↗

We find sufficient conditions for the absence of harmonic L2L^2 spinors on spin manifolds constructed as cone bundles over a compact Kähler base. These conditions are fulfilled for certain perturbations of the Euclidean metric, and also for the generalized Taub-NUT metrics of Iwai-Katayama, thus proving a conjecture of…

2010-03-28abs ↗pdf ↗

We classify all spacetimes with a closed rank-2 conformal Killing-Yano tensor. They give a generalization of Kerr-NUT-de Sitter spacetimes. The Einstein condition is explicitly solved and written as an indefinite integral. It is characterized by a polynomial in the integrand. We briefly discuss the smoothness condition…

2008-05-07abs ↗pdf ↗

The aim of this paper is to present a further contribution to the analysis of absolute convergence (and), associated with the neoclassical theory, and conditional, associated with endogenous growth theory, of the sectoral productivity at regional level. Presenting some empirical evidence of absolute convergence of prod…

2011-10-25abs ↗pdf ↗

This paper provides a classification result for gravitational instantons with cubic volume growth and cyclic fundamental group at infinity. It proves that a complete hyperkähler manifold asymptotic to a circle fibration over the Euclidean three-space is either the standard $\rl^3 \times \sph^1$ or a multi-Taub-NUT mani…

2009-10-30abs ↗pdf ↗

New extremal Kähler metrics found on 4-manifolds with U(2) symmetry.

problem Finding new extremal Kähler metrics on 4-manifolds with U(2) symmetry.
method Analyzing U(2)U(2)-invariant metrics, showing they are conformal to two separate Kähler metrics, leading to ambiKähler structures.
result New complete extremal Kähler metrics found on specific 4-manifolds.