arXiv research

Geometric framework explains deep learning performance.

Bayesian method learns optimal momentum for landmark matching.

Graph clustering method uses templates to match vertices and outperforms classical methods.

Generative models improve CECT template matching reliability.

Method finds multiple noisy graph templates in large graphs.

Designs a Cellular Automata rule for forming touching loop patterns.

Paper tackles curve pattern identification from fragmented cultural heritage objects.

SrvfNet aligns multiple functional data to templates without supervision.

Gradient flow on diffeomorphisms for image registration, with well-posedness proven.

Hopfield networks improve reaction template prediction for few/zero-shot scenarios.

Improved binning technique boosts nUV measure performance.

New method uses image registration to recover complex signals from amplitude data.

A new method for tracking objects using diverse templates.

Two supervised methods classify single-molecule patterns from X-ray imaging.

G2Gs transforms target molecules into reactants without templates, improving accuracy.

Study on well-posedness of EPDiff equations with pseudo-differential inertia.

The paper explores a new method for landmark matching using sub-Riemannian geometry and neural networks.

New algorithm tackles adversarial contextual bandits using stochastic smoothing.

We study completeness properties of the Sobolev diffeomorphism groups $\mathcal D^s(M)$ endowed with strong right-invariant Riemannian metrics when the underlying manifold $M$ is $\mathbb R^d$ or compact without boundary. The main result is that for $s > \dim M/2 + 1$, the group $\mathcal D^s(M)$ is geodesically and me…

CNN-DTW system improves keyword spotting in under-resourced languages.

Generative model uses ODEs and RKHSs for measure matching.

Templates are branched 2-manifolds with semi-flows used to model `chaotic' hyperbolic invariant sets of flows on 3-manifolds. Knotted orbits on a template correspond to those in the original flow. Birman and Williams conjectured that for any given template the number of prime factors of the knots realized would be boun…

We address the following problem: given two smooth densities on a manifold, find an optimal diffeomorphism that transforms one density into the other. Our framework builds on connections between the Fisher-Rao information metric on the space of probability densities and right-invariant metrics on the infinite-dimension…

METRO predicts reactions using minimal templates, reducing computational overhead and achieving state-of-the-art results.

A new KD layer lets student models learn and apply teacher knowledge explicitly.

Unified framework for imitation learning via moment matching.

We consider the use of the Joint Clustering and Matching (JCM) procedure for the supervised classification of a flow cytometric sample with respect to a number of predefined classes of such samples. The JCM procedure has been proposed as a method for the unsupervised classification of cells within a sample into a numbe…

New method to classify simple Smale flows on $S^3$.

NeuralFLoC unifies registration and clustering of functional data, overcoming phase variation challenges.

Dasgupta and Shulman showed that a two-round variant of the EM algorithm can learn mixture of Gaussian distributions with near optimal precision with high probability if the Gaussian distributions are well separated and if the dimension is sufficiently high. In this paper, we generalize their theory to learning mixture…

We describe the Williams zeta functions and the twist zeta functions of sub-Lorenz templates generated by renormalizable Lorenz maps, in terms of the corresponding zeta-functions of the sub-Lorenz templates generated by the renormalized map and by the map that determines the renormalization type.

New algorithms minimize regret in SSP with optimal sparse updates.

Neural production systems learn visual dynamics by applying rule templates to entities.

New model predicts chemical reactions with conditional graph logic networks.

With increasing concerns about security, the need for highly secure physical biometrics-based authentication systems utilizing \emph{cancelable biometric} technologies is on the rise. Because the problem of cancelable template generation deals with the trade-off between template security and matching performance, many …

A flexible machine learning model infers the morphology of the Galactic Center Excess.

IsoNN learns graph representations without node order constraints.

Registration, which aims to find an optimal 1-1 correspondence between shapes, is an important process in different research areas. Conformal mappings have been widely used to obtain a diffeomorphism between shapes that minimizes angular distortion. Conformal registrations are beneficial since it preserves the local ge…

The fact that the modular template coincides with the Lorenz template, discovered by Ghys, implies modular knots have very peculiar properties. We obtain a generalization of these results to other Hecke triangle groups. In this context, the geodesic flow can never be seen as a flow on a subset of $S^3$, and one is led …

Paper addresses data reconstruction from privacy-protected templates using STCA.

End-to-end neural network improves QbE-STD in multilingual speech search.

GPCDL uses Gaussian Processes to learn smooth templates from data.

Paper introduces template functions for featurizing persistence diagrams.

The paper extends LDDMM framework to include Lie group actions in large deformation shape registration.

Adaptive template systems improve feature extraction from persistence diagrams for machine learning.

Generative adversarial network creates motion templates for agent training.

Anosov diffeomorphisms with integrable subbundles have coherent dynamics and spectral rigidity.

Unified approach to shape matching using optimal control.