This paper tackles generating manifold-valued images using WGAN.
problem Generating manifold-valued images over natural images.
method Formulated a theorem of optimal transport for Wasserstein distance on manifolds, introduced a new WGAN framework.
result Proposed model generates more plausible manifold-valued images than competitors.
This paper morphs images on manifold-valued spaces using discrete geodesics.
problem Morphing manifold-valued images with discrete geodesics.
method Time discrete geodesic paths model, numerical minimization alternating between deformations and images.
result Existence of minimizing sequences for morphing manifold-valued images.
Proposes a normalization technique for manifold valued data.
problem Instability in optimization for manifold valued data.
method Develops a general normalization technique for manifold valued data.
result Demonstrates performance gain in synthetic and real datasets.
Proposes CC-NMDF for analyzing manifold-valued data.
problem Nonlinear structure in manifold-valued data requires new analysis methods.
method Curvature-corrected nonnegative manifold data factorization (CC-NMDF) with an iterative algorithm.
result Demonstrates CC-NMDF on real-world diffusion tensor MRI data.
We consider the topic of multivariate regression on manifold-valued output, that is, for a multivariate observation, its output response lies on a manifold. Moreover, we propose a new regression model to deal with the presence of grossly corrupted manifold-valued responses, a bottleneck issue commonly encountered in pr…
This paper develops a method to learn lower-dimensional submanifolds of brain connectomes.
problem Learning lower-dimensional representations of manifold-valued data, especially brain connectomes.
method Riemannian variational autoencoder with intrinsic generative model.
result The method can learn weighted submanifolds of manifold-valued data.
The paper tackles variational regularization for manifold-valued data in inverse problems.
problem Inverse problems for manifold-valued data with indirect measurements.
method TV and TGV regularization for manifold-valued data, well-posedness analysis, numerical algorithms.
result Experimental results demonstrate the potential of the proposed schemes.
An increasing array of biomedical and computer vision applications requires the predictive modeling of complex data, for example images and shapes. The main challenge when predicting such objects lies in the fact that they do not comply to the assumptions of Euclidean geometry. Rather, they occupy non-linear spaces, a.…
Hierarchical geodesic model for analyzing shapes on manifolds.
problem Analyzing temporal observations on manifold-valued data.
method Adapted functional-based metric for efficiency; variational time discretization of geodesics.
result Performed hypothesis tests and estimated mean trends in longitudinal analysis.
Extends graph theory to hypergraphs with manifold-valued nodes.
problem Representing complex N-ary relationships on manifolds.
method Defined function spaces and symmetric products for manifold-valued nodes and edges.
result Generalized hypergraph Laplacians to manifold-valued hypergraphs.
Proposes a new technique for VAEs using manifold-valued variables.
problem Effect of prior distribution choice on VAE learning capacity.
method Embedding-reparameterization procedure (ER) for manifold-valued latent variables.
result ER technique outperforms conventional VAE on a toy benchmark.
We approximate derivatives of functions on manifolds by embedding them and applying vector-valued operators.
problem Derivatives of manifold-valued functions are harder to approximate than vector-valued functions.
method Embed the manifold into a higher space, approximate the derivative of the vector-valued function, and project back.
result We provide error bounds for the approximation of manifold-valued function derivatives.
Study on completeness of Sobolev metrics on manifold-valued curves.
problem Completeness of Sobolev metrics on spaces of manifold-valued curves.
method Analysis of reparametrization invariant Sobolev metrics of order n≥2. result Sobolev immersions are metrically and geodesically complete for several important cases of metrics.
We use splines and the Sasaki metric to analyze and compare manifold-valued trajectories.
problem Analyzing and comparing trajectories on Riemannian manifolds.
method Riemannian hierarchical model, Bézier splines, Sasaki metric.
result Spline-based approaches outperform state-of-the-art methods in intensity classification of trajectories.
Wavelet-based method for sparse data on manifolds.
problem Sparse representation of manifold-valued data.
method Interpolatory wavelet/multiscale transform for sparse regularization.
result Well-posedness of variational models and successful numerical algorithms.
Develops intrinsic Gaussian process regression for manifold-valued data.
problem Lack of intrinsic Gaussian process methods for manifold-valued response variables.
method Proposes an intrinsic covariance structure and a novel intrinsic Gaussian process regression model.
result Establishes asymptotic properties and shows posterior consistency.
Study Lipschitz regularity for manifold-constrained ROF model on curved surfaces.
problem Lipschitz regularity for manifold-constrained ROF model on curved surfaces.
method Generalization of ROF model, existence and uniqueness of minimizers, regularity results on PDE system.
result Lipschitz regularity of minimizers without convexity requirements.
The present contribution suggests the use of a multidimensional scaling (MDS) algorithm as a visualization tool for manifold-valued elements. A visualization tool of this kind is useful in signal processing and machine learning whenever learning/adaptation algorithms insist on high-dimensional parameter manifolds.
New method classifies manifold-valued data using Riemannian geometry.
problem Classifying data on curved Riemannian manifolds.
method Probabilistic Learning Vector Quantization on Symmetric Positive Definite Matrices.
result The method outperforms traditional Euclidean methods on manifold-valued data.
Proposes graph neural network layers for manifold-valued graphs.
problem Graphs with features in a Riemannian manifold.
method Diffusion layer and tangent multilayer perceptron.
result Outperforms state-of-the-art networks on Alzheimer's classification.
We discuss multiscale representations of discrete manifold-valued data. As it turns out that we cannot expect general manifold-analogues of biorthogonal wavelets to possess perfect reconstruction, we focus our attention on those constructions which are based on upscaling operators which are either interpolating or midp…
The paper analyzes the amplitude of functions on the sphere, improving FDA methods.
problem Analyzing trajectories on non-linear manifolds with time variability.
method Developed tools for temporal alignment, geodesic computation, and mean calculation on S2. result Efficient and accurate tools for analyzing manifold-valued functions on S2. We discuss the nature of structure-preserving maps of varies function algebras. In particular, we identify isomorphisms between special Colombeau algebras on manifolds with invertible manifold-valued generalized functions in the case of smooth parametrization. As a consequence, and to underline the consistency and vali…
A new method calculates intrinsic effective sample size for manifold-valued data.
problem Challenges in choosing effective sample size for manifold-valued data.
method Proposes an intrinsic effective sample size based on kernel discrepancy.
result Establishes an exact finite-sample risk interpretation and consistency of the estimator.
Two methods for interpolating manifold-valued data are presented.
problem Interpolating manifold-valued functions with derivative constraints.
method Two approaches: weighted Riemannian barycenters and tangent space interpolation.
result Both methods are valid and perform well with numerical examples.
Develops methods to find most probable paths on complex manifolds.
problem Identifying optimal paths for manifold-valued processes, especially those with non-trivial structures.
method Constructs a general approach to defining and identifying most probable paths by measuring the Onsager-Machlup function on the anti-development of such processes.
result Derives explicit equations for development most probable paths that encompass various manifold-valued processes.
Develops a curvature-corrected tangent space method for manifold-valued data.
problem Generalizing real-valued data approximation to manifold-valued data.
method Systematic approach to developing global-geometry aware, computationally feasible approximation schemes.
result Proposes CC-tHOSVD for low-rank approximation of manifold-valued data.
New method for predicting portfolio dynamics using non-Euclidean geometry.
problem Predicting efficient portfolios with geometric structure.
method Non-Euclidean conditional expectation and filtering equations.
result Accurate numerical forecasts of portfolio dynamics.
Researchers enhance hyperspherical latent representations for higher-dimensional data.
problem Limited expressivity of hyperspherical vMF distribution in high dimensions.
method Use a product-space to extend hyperspherical parameterizations to higher dimensions.
result Improved results on image datasets compared to traditional methods.
Introduces intrinsic Riemannian cross-covariance for manifold-valued random objects.
problem Covariance estimation for random objects on Riemannian manifolds.
method Defines covariance and correlation via parallel transport.
result Proposed covariance is independent of coordinate choices.
The paper tackles VAEs with manifold-valued latent variables.
problem VAEs struggle with non-trivial manifold topologies.
method Extended reparameterization trick to Lie groups, focusing on SO(3). result Manifold-valued latent variables preserve topological structure.
Extends structured prediction to continuous manifold valued regression.
problem Continuous manifold valued regression problems.
method Geometric optimization for manifold valued regression.
result Statistical consistency of the proposed approach.
Unified framework for Riemannian deep learning across manifold-valued representations.
problem Deep learning on manifold-valued representations often relies on Euclidean approximations or costly geometric operations.
method Develops reusable neural modules, manifold-specific network architectures, and geometric designs.
result Generalizes batch normalization and multinomial logistic regression to broader classes of manifolds.
Unified framework for Riemannian deep learning across manifold-valued representations.
problem Deep learning on manifold-valued data lacks reusable modules, specific network architectures, and efficient geometric operations.
method Develops reusable neural modules, manifold-specific network architectures, and geometric designs for broad classes of Lie groups and gyrogroups.
result Generalizes batch normalization and multinomial logistic regression to Riemannian manifolds, including SPD and hyperbolic spaces.
Paper adapts numerical scheme for parallel transport on diffeomorphism manifolds.
problem Efficient computation of parallel transport on high-dimensional manifold-valued data.
method Adapts a numerical scheme for parallel transport to finite-dimensional manifolds of diffeomorphisms.
result Qualitative and quantitative analysis of scheme's behavior on high-dimensional manifolds.
Paper computes optimal matching between curves on manifolds.
problem Matching curves on infinite-dimensional manifolds.
method Geodesic computation using Riemannian metric and quotient structure.
result Algorithm for computing geodesics in shape space.
Extends Whitney's theorem for functions on rough boundaries.
problem Global extension of manifold-valued functions on domains with rough boundaries.
method Using locally convex spaces of compactly-supported sections of vector bundles, proving the existence of an extension operator.
result The restriction map from everywhere-defined functions is a submersion, allowing local linear splittings.
The paper develops efficient sampling strategies for BRDF data manifolds.
problem Efficiently sampling and measuring BRDF data from high-dimensional manifolds.
method Statistical design of experiments and generalized proactive learning.
result Established more efficient sampling and measurement strategies for BRDF data manifolds.
This paper derives radial fields on manifolds of symmetric positive definite matrices.
problem Lack of an expression for radial fields on manifolds of symmetric positive definite matrices.
method Derives an expression for radial fields on manifolds of symmetric positive definite matrices.
result Derives an expression for radial fields on manifolds of symmetric positive definite matrices.
Improved Kalman filter for Stiefel manifold measurements.
problem Improving accuracy in measurements on Stiefel manifolds.
method Generalization of extended Kalman filter for Stiefel manifold-valued measurements.
result Significant improvement over raw measurements.
A new method learns manifold-valued latents without an encoder.
problem Distorting data with intrinsic non-Euclidean structure.
method Riemannian generative decoder that learns latents directly.
result Learned representations respect the prescribed geometry and capture intrinsic non-Euclidean structure.
This paper extends Nevanlinna's unicity theorems to complete Kahler manifolds.
problem Generalizing Nevanlinna's unicity theorems to non-compact Kahler manifolds.
method Applying the theorems to complete Kahler manifolds with specific curvature conditions.
result Generalized Nevanlinna's unicity theorems for specific types of Kahler manifolds.
Researchers extend ResNets to Riemannian manifolds, improving performance over existing methods.
problem Learning on Riemannian manifolds, especially for hierarchical graphs and manifold-valued data.
method Geometrically principled extension of ResNets to general Riemannian manifolds.
result Riemannian ResNets outperform existing manifold neural networks in relevant metrics and training dynamics.
Study large deviations for hypoelliptic diffusion on sub-Riemannian manifolds.
problem Large deviations for hypoelliptic diffusion measures on sub-Riemannian manifolds.
method Rough path theory and manifold-valued Malliavin calculus.
result Proved a large deviation principle for pinned hypoelliptic diffusion measures.
The aim of this paper is to find an optimal matching between manifold-valued curves, and thereby adequately compare their shapes, seen as equivalent classes with respect to the action of reparameterization. Using a canonical decomposition of a path in a principal bundle, we introduce a simple algorithm that finds an op…
Study of elastic models in non-Euclidean spaces via Γ-convergence.
problem Elasticity in non-Euclidean ambient spaces with incompatible local rest distances.
method Γ-convergence to derive a limit elastic model, relating minimum energy to curvature discrepancy.
result Linearized version of a conjecture in elasticity confirmed, linking energy to curvature.
Model learns spatiotemporal patterns on graphs from longitudinal data.
problem Learning spatiotemporal patterns on graphs from longitudinal data.
method Mixed-effects model with stochastic Expectation-Maximization algorithm (MCMC-SAEM).
result Personalized model accurately predicts cortical thickness maps in patients.
Paper proves convergence of Kalman filter on Stiefel manifolds with measurement errors.
problem Filtering constant particle with measurement errors on Stiefel manifolds.
method Extended Kalman filter applied to Stiefel manifold-valued observations.
result Convergence of the extended Kalman filter proved for constant system process.