Research
On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

168,694 papers · 148 categories

Trend · papers per month

3587171,0751,433 · Jun 202019922001200920172026
48 results for hyperbolic models

Crochet models of a hyperbolic plane is a popular educational tool as they help to visualize complicated objets in hyperbolic geometry. We present another way how to make crochet models when we view them as a part of a triangulated hyperbolic plane. We also provide a model of a cylinder in a hyperbolic space. This appr…

2019-10-14abs ↗pdf ↗

Simple Euclidean models outperform hyperbolic graph learning models.

problem The effectiveness of hyperbolic graph learning models is questioned.
method Careful analysis of hyperbolic graph representation learning, identifying and addressing issues with baselines, modeling assumptions, and metric usage.
result Simple Euclidean models often outperform hyperbolic graph learning models, even on hyperbolic datasets.

By using Klein's model for hyperbolic geometry, hyperbolic structures on orbifolds or manifolds provide examples of real projective structures. By Andreev's theorem, many 3-dimensional reflection orbifolds admit a finite volume hyperbolic structure, and such a hyperbolic structure is unique. However, the induced real p…

2010-03-23abs ↗pdf ↗

This paper improves probabilistic latent models on hyperbolic spaces.

problem Uncertainty in predictions due to geodesics crossing low-data regions.
method Augmenting hyperbolic manifold with a pullback metric for probabilistic pullback metrics.
result Geodesics on pullback metric respect both geometry and data distribution, reducing uncertainty.

Upper bound for Hausdorff distance between hyperbolic space and its medianization.

problem Calculating the Hausdorff distance between hyperbolic space and its medianization.
method Using de Sitter space to model finite-dimensional hyperbolic space and its medianization, calculating the Hausdorff distance.
result An upper bound for the Hausdorff distance between hyperbolic space and its medianization is calculated.

We present a large scale hyperbolic recommender system. We discuss why hyperbolic geometry is a more suitable underlying geometry for many recommendation systems and cover the fundamental milestones and insights that we have gained from its development. In doing so, we demonstrate the viability of hyperbolic geometry f…

2019-02-22abs ↗pdf ↗

The Funk-Finsler structure is constructed in hyperbolic models, including the Klein unit disc.

problem Constructing Funk-Finsler structures in hyperbolic models.
method Using Finsler isometries and explicit computations, the Funk-Finsler structure is constructed in various hyperbolic models.
result The Funk-Finsler structure in the Klein unit disc is a Randers metric.

Extending BTZ models to complete hyperbolic surfaces.

problem Extending BTZ models to complete hyperbolic surfaces.
method Proving a parametrization result for globally hyperbolic Cauchy-maximal and Cauchy-compact locally Minkowski manifolds with extreme BTZ.
result The tangent bundle of the Teichmüller space parametrizes globally hyperbolic Cauchy-maximal and Cauchy-compact locally Minkowski manifolds with extreme BTZ.

We introduce a number of new tools for the study of relatively hyperbolic groups. First, given a relatively hyperbolic group G, we construct a nice combinatorial Gromov hyperbolic model space acted on properly by G, which reflects the relative hyperbolicity of G in many natural ways. Second, we construct two useful bic…

2006-01-13abs ↗pdf ↗

Hyperbolic spaces have recently gained momentum in the context of machine learning due to their high capacity and tree-likeliness properties. However, the representational power of hyperbolic geometry is not yet on par with Euclidean geometry, mostly because of the absence of corresponding hyperbolic neural network lay…

2018-05-23abs ↗pdf ↗

A new framework for hyperbolic neural networks using the Klein model is introduced.

problem Previous works focused on Poincaré and hyperboloid models, neglecting the Klein model.
method Formulation of operations using the Klein model, study of the Klein linear layer, and comparison with Poincaré ball model.
result The Klein HNN performs similarly to the Poincaré ball model, offering a third option.

BIGUE algorithm provides credible intervals for hyperbolic network embeddings.

problem Uncertainty in hyperbolic network embeddings.
method Markov chain Monte Carlo (MCMC) algorithm for Bayesian hyperbolic random graph model.
result Samples from the posterior distribution provide credible intervals for hyperbolic coordinates and network properties.

Improves few-shot learning for hierarchical data using hyperbolic space.

problem Few-shot class-incremental learning for hierarchical data.
method Contrastive learning in hyperbolic space, Poincaré ball model, hyperbolic contrastive loss, maximum entropy distribution.
result Effective improvement of coarse and fine class accuracies in few-shot conditions.

Improves stability in hyperbolic neural networks for complex data generation.

problem Numerical instability in hyperbolic neural networks hinders complex architecture development.
method Proposes a novel hyperbolic AE-GAN architecture with stable layers.
result Demonstrates state-of-the-art performance in generating complex data.

We consider a volume maximization program to construct hyperbolic structures on triangulated 3-manifolds, for which previous progress has lead to consider angle assignments which do not correspond to a hyperbolic metric on each simplex. We show that critical points of the generalized volume are associated to geometric …

2009-08-14abs ↗pdf ↗

The paper connects hyperbolic Dehn surgery and Higgs bundles to construct model objects in representation varieties.

problem Constructing model objects in representation varieties for Higgs bundles.
method Reviewing hyperbolic Dehn surgery and bending procedures, and applying them to Higgs bundles.
result Explicit examples of model objects in representation varieties are produced.

In 1900, Macfarlane proposed a hyperbolic variation on Hamilton's quaternions that closely resembles Minkowski spacetime. Viewing this in a modern context, we expand upon Macfarlane's idea and develop a model for real hyperbolic 3-space in which both points and isometries are expressed as complex quaternions, analogous…

2017-01-24abs ↗pdf ↗

Graph neural network (GNN) has shown superior performance in dealing with graphs, which has attracted considerable research attention recently. However, most of the existing GNN models are primarily designed for graphs in Euclidean spaces. Recent research has proven that the graph data exhibits non-Euclidean latent ana…

2019-12-06abs ↗pdf ↗

This work improves KG embeddings by integrating hyperbolic and attention mechanisms.

problem Preserving hierarchical and logical patterns in KGs with low-dimensional embeddings.
method Combines hyperbolic reflections/rotations with attention mechanisms to capture complex relational patterns.
result Improves MRR by up to 6.1% on standard benchmarks and new state-of-the-art results in high dimensions.

This work tackles manifold regression onto hyperbolic space for tree classification and taxonomy extension.

problem Performing manifold-valued regression onto an hyperbolic space for tree classification and taxonomy extension.
method Formulated as a manifold regression task in hyperbolic space, proposed a parametric deep learning model and a non-parametric kernel method.
result Hyperbolic-based estimators significantly outperform Euclidean space methods in taxonomy expansion.

APo-VAE generates text in hyperbolic space for better hierarchical representation.

problem Lack of hierarchical structure in Euclidean embeddings for natural language.
method Adversarial Poincare Variational Autoencoder (APo-VAE) in hyperbolic latent space.
result APo-VAE outperforms Euclidean VAEs in capturing latent language hierarchies.

New research shows hyperbolic embeddings are useful for global consistency tasks in graphs.

problem The usefulness of hyperbolic representations in graph learning tasks.
method Computed hyperbolic embeddings for node classification and link prediction tasks, addressing optimization issues at zero curvature.
result Hyperbolic embeddings are more effective for tasks requiring global consistency, while Euclidean models are superior for other tasks.

Classifies self-similar curve shortening flows in hyperbolic 2-space.

problem Classifying self-similar curve shortening flows in hyperbolic 2-space.
method Analyzes and classifies solutions in hyperbolic 2-space.
result Completes the classification of self-similar curve shortening flows in constant curvature model spaces in 2-dimensions.

The paper defines two types of hyperbolicity for complex manifolds and proves related results.

problem Defining and studying hyperbolicity for a broader class of complex manifolds.
method Introducing SKT hyperbolicity and Gauduchon hyperbolicity, proving results using SKT and Gauduchon metrics.
result Every SKT hyperbolic manifold is also Kobayashi/Brody hyperbolic and every Gauduchon hyperbolic manifold is divisorially hyperbolic.

Study geometry of tetrahedra in complex hyperbolic space and Hilbert spaces.

problem Understanding geometric relationships between complex hyperbolic spaces and Hilbert spaces.
method Use a complex analog of the cosine of a vertex angle as a novel technical tool.
result Describe possible triangular faces of tetrahedra in hyperbolic space and three-dimensional subspaces in Hilbert spaces with Pick kernels.

Extends growth properties of hyperbolic groups to their extensions.

problem Quantifying subgroup alternatives in group laws.
method Develops a framework for preserving exponential growth in extensions of hyperbolic groups.
result Automorphism groups of certain hyperbolic and Artin groups have locally uniform exponential growth.