Measure transfer via stochastic slicing and matching
- URL: http://arxiv.org/abs/2307.05705v1
- Date: Tue, 11 Jul 2023 18:12:30 GMT
- Title: Measure transfer via stochastic slicing and matching
- Authors: Shiying Li and Caroline Moosmueller
- Abstract summary: This paper studies iterative schemes for measure transfer and approximation problems defined through a slicing-and-matching procedure.
The main contribution of this paper is an almost sure convergence proof for slicing-and-matching schemes.
- Score: 1.4594704809280983
- License: http://creativecommons.org/licenses/by-nc-nd/4.0/
- Abstract: This paper studies iterative schemes for measure transfer and approximation
problems, which are defined through a slicing-and-matching procedure. Similar
to the sliced Wasserstein distance, these schemes benefit from the availability
of closed-form solutions for the one-dimensional optimal transport problem and
the associated computational advantages. While such schemes have already been
successfully utilized in data science applications, not too many results on
their convergence are available. The main contribution of this paper is an
almost sure convergence proof for stochastic slicing-and-matching schemes. The
proof builds on an interpretation as a stochastic gradient descent scheme on
the Wasserstein space. Numerical examples on step-wise image morphing are
demonstrated as well.
Related papers
- Efficient Trajectory Inference in Wasserstein Space Using Consecutive Averaging [3.8623569699070353]
Trajectory inference deals with the challenge of reconstructing continuous processes from such observations.
We propose methods for B-spline approximation of point clouds through consecutive averaging that is instrinsic to the Wasserstein space.
We rigorously evaluate our method by providing convergence guarantees and testing it on simulated cell data.
arXiv Detail & Related papers (2024-05-30T04:19:20Z) - Towards Efficient Time Stepping for Numerical Shape Correspondence [55.2480439325792]
Methods based on partial differential equations (PDEs) have been established, encompassing e.g. the classic heat kernel signature.
We consider here several time stepping schemes. The goal of this investigation is to assess, if one may identify a useful property of methods for time integration for the shape analysis context.
arXiv Detail & Related papers (2023-12-21T13:40:03Z) - Approximation properties of slice-matching operators [3.408452800179907]
Iterative slice-matching procedures are efficient schemes for transferring a source measure to a target measure, especially in high dimensions.
We explore approximation properties related to a single step of such schemes by examining an associated slice-matching operator.
arXiv Detail & Related papers (2023-10-16T22:32:43Z) - Isotropic Gaussian Processes on Finite Spaces of Graphs [71.26737403006778]
We propose a principled way to define Gaussian process priors on various sets of unweighted graphs.
We go further to consider sets of equivalence classes of unweighted graphs and define the appropriate versions of priors thereon.
Inspired by applications in chemistry, we illustrate the proposed techniques on a real molecular property prediction task in the small data regime.
arXiv Detail & Related papers (2022-11-03T10:18:17Z) - Object Representations as Fixed Points: Training Iterative Refinement
Algorithms with Implicit Differentiation [88.14365009076907]
Iterative refinement is a useful paradigm for representation learning.
We develop an implicit differentiation approach that improves the stability and tractability of training.
arXiv Detail & Related papers (2022-07-02T10:00:35Z) - Sliced-Wasserstein Gradient Flows [15.048733056992855]
Minimizing functionals in the space of probability distributions can be done with Wasserstein gradient flows.
This work proposes to use gradient flows in the space of probability measures endowed with the sliced-Wasserstein distance.
arXiv Detail & Related papers (2021-10-21T08:34:26Z) - Asymmetric compressive learning guarantees with applications to
quantized sketches [15.814495790111323]
We present a framework to train audio event classification on large-scale datasets.
We study the relaxation where this map is allowed to be different for each phase.
We then instantiate this framework to the setting of quantized sketches, by proving that the LPD indeed holds for binary sketch contributions.
arXiv Detail & Related papers (2021-04-20T15:37:59Z) - Pathwise Conditioning of Gaussian Processes [72.61885354624604]
Conventional approaches for simulating Gaussian process posteriors view samples as draws from marginal distributions of process values at finite sets of input locations.
This distribution-centric characterization leads to generative strategies that scale cubically in the size of the desired random vector.
We show how this pathwise interpretation of conditioning gives rise to a general family of approximations that lend themselves to efficiently sampling Gaussian process posteriors.
arXiv Detail & Related papers (2020-11-08T17:09:37Z) - Continuous Regularized Wasserstein Barycenters [51.620781112674024]
We introduce a new dual formulation for the regularized Wasserstein barycenter problem.
We establish strong duality and use the corresponding primal-dual relationship to parametrize the barycenter implicitly using the dual potentials of regularized transport problems.
arXiv Detail & Related papers (2020-08-28T08:28:06Z) - Conditional gradient methods for stochastically constrained convex
minimization [54.53786593679331]
We propose two novel conditional gradient-based methods for solving structured convex optimization problems.
The most important feature of our framework is that only a subset of the constraints is processed at each iteration.
Our algorithms rely on variance reduction and smoothing used in conjunction with conditional gradient steps, and are accompanied by rigorous convergence guarantees.
arXiv Detail & Related papers (2020-07-07T21:26:35Z)
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.