A diffusion approach to Stein's method on Riemannian manifolds
- URL: http://arxiv.org/abs/2003.11497v3
- Date: Thu, 27 Apr 2023 09:21:42 GMT
- Title: A diffusion approach to Stein's method on Riemannian manifolds
- Authors: Huiling Le, Alexander Lewis, Karthik Bharath and Christopher Fallaize
- Abstract summary: We exploit the relationship between the generator of a diffusion on $mathbf M$ with target invariant measure and its characterising Stein operator.
We derive Stein factors, which bound the solution to the Stein equation and its derivatives.
We imply that the bounds for $mathbb Rm$ remain valid when $mathbf M$ is a flat manifold.
- Score: 65.36007959755302
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: We detail an approach to develop Stein's method for bounding integral metrics
on probability measures defined on a Riemannian manifold $\mathbf M$. Our
approach exploits the relationship between the generator of a diffusion on
$\mathbf M$ with target invariant measure and its characterising Stein
operator. We consider a pair of such diffusions with different starting points,
and through analysis of the distance process between the pair, derive Stein
factors, which bound the solution to the Stein equation and its derivatives.
The Stein factors contain curvature-dependent terms and reduce to those
currently available for $\mathbb R^m$, and moreover imply that the bounds for
$\mathbb R^m$ remain valid when $\mathbf M$ is a flat manifold
Related papers
- On Wasserstein distances for affine transformations of random vectors [1.2836088204932843]
We give concrete lower bounds for rotated copies of random vectors in $mathbbR2$.
We derive upper bounds for compositions of affine maps which yield a fruitful variety of diffeomorphisms applied to an initial data measure.
We give a framework for mimicking handwritten digit or alphabet datasets that can be applied in a manifold learning framework.
arXiv Detail & Related papers (2023-10-05T23:30:41Z) - Properties of Discrete Sliced Wasserstein Losses [11.280151521887076]
The Sliced Wasserstein (SW) distance has become a popular alternative to the Wasserstein distance for comparing probability measures.
Widespread applications include image processing, domain adaptation and generative modelling, where it is common to optimise some parameters in order to minimise SW.
We investigate the regularity and optimisation properties of this energy, as well as its Monte-Carlo approximation $mathcalE_p$.
arXiv Detail & Related papers (2023-07-19T21:21:18Z) - Statistical Learning under Heterogeneous Distribution Shift [71.8393170225794]
Ground-truth predictor is additive $mathbbE[mathbfz mid mathbfx,mathbfy] = f_star(mathbfx) +g_star(mathbfy)$.
arXiv Detail & Related papers (2023-02-27T16:34:21Z) - The Sketched Wasserstein Distance for mixture distributions [13.643197515573029]
Sketched Wasserstein Distance ($WS$) is a new probability distance specifically tailored to finite mixture distributions.
We show that $WS$ is defined to be the most discriminative of this metric to the space $mathcalS = textrmconv(mathcalA)$ of mixtures of elements of $mathcalA$.
arXiv Detail & Related papers (2022-06-26T02:33:40Z) - q-Paths: Generalizing the Geometric Annealing Path using Power Means [51.73925445218366]
We introduce $q$-paths, a family of paths which includes the geometric and arithmetic mixtures as special cases.
We show that small deviations away from the geometric path yield empirical gains for Bayesian inference.
arXiv Detail & Related papers (2021-07-01T21:09:06Z) - Large-Scale Wasserstein Gradient Flows [84.73670288608025]
We introduce a scalable scheme to approximate Wasserstein gradient flows.
Our approach relies on input neural networks (ICNNs) to discretize the JKO steps.
As a result, we can sample from the measure at each step of the gradient diffusion and compute its density.
arXiv Detail & Related papers (2021-06-01T19:21:48Z) - Wasserstein distance estimates for the distributions of numerical
approximations to ergodic stochastic differential equations [0.3553493344868413]
We study the Wasserstein distance between the in distribution of an ergodic differential equation and the distribution in the strongly log-concave case.
This allows us to study in a unified way a number of different approximations proposed in the literature for the overdamped and underdamped Langevin dynamics.
arXiv Detail & Related papers (2021-04-26T07:50:04Z) - Bayesian Quadrature on Riemannian Data Manifolds [79.71142807798284]
A principled way to model nonlinear geometric structure inherent in data is provided.
However, these operations are typically computationally demanding.
In particular, we focus on Bayesian quadrature (BQ) to numerically compute integrals over normal laws.
We show that by leveraging both prior knowledge and an active exploration scheme, BQ significantly reduces the number of required evaluations.
arXiv Detail & Related papers (2021-02-12T17:38:04Z) - A Non-Asymptotic Analysis for Stein Variational Gradient Descent [44.30569261307296]
We provide a novel finite time analysis for the Stein Variational Gradient Descent algorithm.
We provide a descent lemma establishing that the algorithm decreases the objective at each iteration.
We also provide a convergence result of the finite particle system corresponding to the practical implementation of SVGD to its population version.
arXiv Detail & Related papers (2020-06-17T12:01:33Z) - Robustly Learning any Clusterable Mixture of Gaussians [55.41573600814391]
We study the efficient learnability of high-dimensional Gaussian mixtures in the adversarial-robust setting.
We provide an algorithm that learns the components of an $epsilon$-corrupted $k$-mixture within information theoretically near-optimal error proofs of $tildeO(epsilon)$.
Our main technical contribution is a new robust identifiability proof clusters from a Gaussian mixture, which can be captured by the constant-degree Sum of Squares proof system.
arXiv Detail & Related papers (2020-05-13T16:44:12Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.