Leveraging Optimal Transport via Projections on Subspaces for Machine
Learning Applications
- URL: http://arxiv.org/abs/2311.13883v1
- Date: Thu, 23 Nov 2023 10:13:07 GMT
- Title: Leveraging Optimal Transport via Projections on Subspaces for Machine
Learning Applications
- Authors: Cl\'ement Bonet
- Abstract summary: In this thesis, we focus on alternatives which use projections on subspaces.
The main such alternative is the Sliced-Wasserstein distance.
Back to the original Euclidean Sliced-Wasserstein distance between probability measures, we study the dynamic of gradient flows.
- Score: 0.0
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Optimal Transport has received much attention in Machine Learning as it
allows to compare probability distributions by exploiting the geometry of the
underlying space. However, in its original formulation, solving this problem
suffers from a significant computational burden. Thus, a meaningful line of
work consists at proposing alternatives to reduce this burden while still
enjoying its properties. In this thesis, we focus on alternatives which use
projections on subspaces. The main such alternative is the Sliced-Wasserstein
distance, which we first propose to extend to Riemannian manifolds in order to
use it in Machine Learning applications for which using such spaces has been
shown to be beneficial in the recent years. We also study sliced distances
between positive measures in the so-called unbalanced OT problem. Back to the
original Euclidean Sliced-Wasserstein distance between probability measures, we
study the dynamic of gradient flows when endowing the space with this distance
in place of the usual Wasserstein distance. Then, we investigate the use of the
Busemann function, a generalization of the inner product in metric spaces, in
the space of probability measures. Finally, we extend the subspace detour
approach to incomparable spaces using the Gromov-Wasserstein distance.
Related papers
- Sliced-Wasserstein Distances and Flows on Cartan-Hadamard Manifolds [13.851780805245477]
We derive general constructions of Sliced-Wasserstein distances on Cartimatan-Hadamard manifold.
We also propose non-parametric schemes to minimize these new distances by approxing their Wasserstein gradient flows.
arXiv Detail & Related papers (2024-03-11T10:01:21Z) - Continuous-time Riemannian SGD and SVRG Flows on Wasserstein Probabilistic Space [17.13355049019388]
We extend the gradient flow on Wasserstein space into the gradient descent (SGD) flow and variance reduction (SVRG) flow.
By leveraging the property of Wasserstein space, we construct differential equations to approximate the corresponding discrete dynamics in Euclidean space.
Our results are proven, which match the results in Euclidean space.
arXiv Detail & Related papers (2024-01-24T15:35:44Z) - Point Cloud Classification via Deep Set Linearized Optimal Transport [51.99765487172328]
We introduce Deep Set Linearized Optimal Transport, an algorithm designed for the efficient simultaneous embedding of point clouds into an $L2-$space.
This embedding preserves specific low-dimensional structures within the Wasserstein space while constructing a classifier to distinguish between various classes of point clouds.
We showcase the advantages of our algorithm over the standard deep set approach through experiments on a flow dataset with a limited number of labeled point clouds.
arXiv Detail & Related papers (2024-01-02T23:26:33Z) - Hyperbolic Sliced-Wasserstein via Geodesic and Horospherical Projections [17.48229977212902]
It has been shown beneficial for many types of data which present an underlying hierarchical structure to be embedded in hyperbolic spaces.
Many tools of machine learning were extended to such spaces, but only few discrepancies to compare probability distributions defined over those spaces exist.
In this work, we propose to derive novel hyperbolic sliced-Wasserstein discrepancies.
arXiv Detail & Related papers (2022-11-18T07:44:27Z) - Neural Bregman Divergences for Distance Learning [60.375385370556145]
We propose a new approach to learning arbitrary Bregman divergences in a differentiable manner via input convex neural networks.
We show that our method more faithfully learns divergences over a set of both new and previously studied tasks.
Our tests further extend to known asymmetric, but non-Bregman tasks, where our method still performs competitively despite misspecification.
arXiv Detail & Related papers (2022-06-09T20:53:15Z) - A Dimensionality Reduction Method for Finding Least Favorable Priors
with a Focus on Bregman Divergence [108.28566246421742]
This paper develops a dimensionality reduction method that allows us to move the optimization to a finite-dimensional setting with an explicit bound on the dimension.
In order to make progress on the problem, we restrict ourselves to Bayesian risks induced by a relatively large class of loss functions, namely Bregman divergences.
arXiv Detail & Related papers (2022-02-23T16:22:28Z) - Supervised learning of sheared distributions using linearized optimal
transport [64.53761005509386]
In this paper we study supervised learning tasks on the space of probability measures.
We approach this problem by embedding the space of probability measures into $L2$ spaces using the optimal transport framework.
Regular machine learning techniques are used to achieve linear separability.
arXiv Detail & Related papers (2022-01-25T19:19:59Z) - Subspace Detours Meet Gromov-Wasserstein [15.048733056992855]
The subspace detour approach was recently presented by Muzellec and Cuturi.
The contribution of this paper is to extend this category of methods to the Gromov-Wasserstein problem.
arXiv Detail & Related papers (2021-10-21T07:04:28Z) - Lifting the Convex Conjugate in Lagrangian Relaxations: A Tractable
Approach for Continuous Markov Random Fields [53.31927549039624]
We show that a piecewise discretization preserves better contrast from existing discretization problems.
We apply this theory to the problem of matching two images.
arXiv Detail & Related papers (2021-07-13T12:31:06Z) - The Unbalanced Gromov Wasserstein Distance: Conic Formulation and
Relaxation [0.0]
Comparing metric measure spaces (i.e. a metric space endowed with aprobability distribution) is at the heart of many machine learning problems.
The most popular distance between such metric spaces is the metric measureGro-Wasserstein (GW) distance of which is a quadratic.
The GW formulation alleviates the comparison of metric spaces equipped with arbitrary positive measures up to isometries.
arXiv Detail & Related papers (2020-09-09T12:38:14Z) - On Projection Robust Optimal Transport: Sample Complexity and Model
Misspecification [101.0377583883137]
Projection robust (PR) OT seeks to maximize the OT cost between two measures by choosing a $k$-dimensional subspace onto which they can be projected.
Our first contribution is to establish several fundamental statistical properties of PR Wasserstein distances.
Next, we propose the integral PR Wasserstein (IPRW) distance as an alternative to the PRW distance, by averaging rather than optimizing on subspaces.
arXiv Detail & Related papers (2020-06-22T14:35:33Z)
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.