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.

168,695 papers · 148 categories

Trend · papers per month

130259389518 · Jun 202019922001200920172026
48 results for hierarchical spaces

A new framework generates large hierarchical search spaces for neural architectures.

problem Discovering neural architectures from simple blocks is hard.
method Context-free grammars for a unified, scalable search space.
result Efficiently searches over complete architectures, outperforming existing methods.

New combinatorial structure for hierarchically hyperbolic spaces.

problem Constructing new hierarchically hyperbolic spaces.
method Combinatorial hierarchical hyperbolicity criterion to construct and clarify HHS structures.
result HHSs admit a combinatorial structure, clarifying the application of the combinatorial HHS criterion.

Unified framework for modeling hierarchical spaces in design problems.

problem Challenges in modeling hierarchical, conditional, heterogeneous, or tree-structured domains.
method Unified framework combining feature modeling and graph theory, introducing meta and partially-decreed variables.
result Demonstrated effectiveness on complex system design problems, including neural networks and green-aircraft.

Two new Hie-TAN and Hie-TAN-Lite algorithms improve TAN for hierarchical feature spaces.

problem Learning dependencies in hierarchical feature spaces.
method Exploits hierarchical parent-child relationships as constraints to learn a dependency tree.
result Hie-TAN-Lite outperforms Hie-TAN and other methods in predictive accuracy.

Improves hierarchical clustering in Euclidean space using autoencoders.

problem Lack of unsupervised methods for learning hierarchical structure in Euclidean space.
method Variational autoencoder with Gaussian mixture prior, rescaling latent space, and Ward's linkage.
result Improved dendrogram purity and Moseley-Wang cost function results.

Hierarchically hyperbolic spaces provide a common framework for studying mapping class groups of finite type surfaces, Teichmüller space, right-angled Artin groups, and many other cubical groups. Given such a space X\mathcal X, we build a bordificationcompatible with the hierarchically hyperbolic structure. If $\mathc…

2016-04-04abs ↗pdf ↗

Hyperbolic space outperforms Euclidean in learning hierarchical data.

problem Learning hierarchical data in Euclidean space requires exponentially many samples.
method Established geometric obstruction in Euclidean space and showed hyperbolic space's advantage.
result Hyperbolic space enables learning with O(mRlogm)O(mR \log m) samples, matching information-theoretic optimum.

Paper develops a new objective for hierarchical clustering in Euclidean space.

problem Hierarchical clustering in Euclidean space with dissimilarity scores.
method Develops a new global objective and connects it to bisecting k-means.
result Optimal 2-means solution approximates the new objective, proving bisecting k-means optimizes a natural global objective.

Stable cubulations and bicombings in mapping class groups and Teichmüller spaces.

problem Understanding geometric structures in mapping class groups and Teichmüller spaces.
method Proving stably approximated by CAT(0) cube complexes, applying to broader colorable hierarchically hyperbolic spaces and groups.
result Stable cubulations and bicombings in mapping class groups and Teichmüller spaces, with stable coarse barycenters.

Proposes a hierarchical curriculum loss to improve model accuracy and interpretability.

problem Flat label spaces in classification algorithms fail to capture dependencies in real-world data.
method Introduces hierarchical curriculum loss with two properties: satisfying hierarchical constraints and providing non-uniform label weights.
result The proposed loss function significantly outperforms multiple baselines on real-world image datasets.

Multicurve stabilizers' extensions are hierarchically hyperbolic.

problem Characterizing the structure of multicurve stabilizers' extensions.
method Proving the extensions of multicurve stabilizers are hierarchically hyperbolic groups.
result Extensions of multicurve stabilizers are hierarchically hyperbolic.

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.

Hierarchically hyperbolic spaces (HHSs) are a large class of spaces that provide a unified framework for studying the mapping class group, right-angled Artin and Coxeter groups, and many 3--manifold groups. We investigate strongly quasiconvex subsets in this class and characterize them in terms of their contracting pro…

2018-09-25abs ↗pdf ↗

Curious hierarchical reinforcement learning improves learning performance.

problem Combining hierarchical abstraction and curiosity-driven exploration in reinforcement learning.
method Developed a method that combines hierarchical reinforcement learning with curiosity.
result Curiosity can more than double learning performance and success rates.

New bicombings found for mapping class groups and Teichmüller spaces.

problem Finding efficient ways to navigate mapping class groups and Teichmüller spaces.
method Explained bicombings via stable cubical intervals in hierarchically hyperbolic spaces.
result Hierarchical hulls are quasi-isometric to finite CAT(0) cube complexes.

Free Random Projection enhances reinforcement learning by naturally incorporating hierarchical structure.

problem Improving reinforcement learning algorithms for better generalization and adaptability.
method Introduces Free Random Projection, a method that uses free probability theory to create random orthogonal matrices encoding hierarchical structure.
result Empirically shows consistent improvement in generalization over standard methods on multi-environment benchmarks.

The joint optimization of representation learning and clustering in the embedding space has experienced a breakthrough in recent years. In spite of the advance, clustering with representation learning has been limited to flat-level categories, which often involves cohesive clustering with a focus on instance relations.…

2019-01-28abs ↗pdf ↗

Fractal Flow enhances normalizing flows with interpretable latent space and hierarchical modeling.

problem High-dimensional density estimation and generative modeling challenges.
method Integrates topic modeling (LDA) and fractal strategy into normalizing flows.
result Achieves latent clustering, controllable generation, and superior estimation accuracy.

The study shows that certain curve graphs are hierarchically hyperbolic but not Gromov hyperbolic.

problem Characterizing the hyperbolicity of curve graphs and their boundaries.
method Using hierarchical hyperbolicity and framed curves, the study examines the properties of curve graphs and their boundaries.
result The curve graphs and their boundaries are hierarchically hyperbolic but not Gromov hyperbolic.

Extends linear representation hypothesis to categorical and hierarchical concepts in LLMs.

problem Representing concepts without natural contrasts in large language models.
method Formalizes linear representation hypothesis for categorical and hierarchical concepts, proving relationships between concept hierarchy and representation geometry.
result Validated theoretical results on large language models, estimating representations for 900+ concepts.

We give several sufficient conditions for uniform exponential growth in the setting of virtually torsion-free hierarchically hyperbolic groups. For example, any hierarchically hyperbolic group that is also acylindrically hyperbolic has uniform exponential growth. In addition, we provide a quasi-isometric characterizati…

2019-09-01abs ↗pdf ↗

In the context of CAT(0) cubical groups, we develop an analogue of the theory of curve complexes and subsurface projections. The role of the subsurfaces is played by a collection of convex subcomplexes called a \emph{factor system}, and the role of the curve graph is played by the \emph{contact graph}. There are a numb…

2014-12-05abs ↗pdf ↗

We provide a simple, combinatorial criteria for a hierarchically hyperbolic space to be relatively hyperbolic by proving a new formulation of relative hyperbolicity in terms of hierarchy structures. In the case of clean hierarchically hyperbolic groups, this criteria characterizes relative hyperbolicity. We apply our c…

2019-05-29abs ↗pdf ↗

Classifies 3-manifold groups with equivariant hierarchically hyperbolic structures.

problem Classifying 3-manifold groups with equivariant hierarchically hyperbolic structures.
method Construction of suitable quasimorphisms on Seifert pieces to construct actions on quasi-lines.
result 3-manifold groups admit equivariant hierarchically hyperbolic structures.

A new drug embedding method using hierarchical drug relations and chemical structures.

problem Learning accurate drug representations from chemical structures and hierarchies.
method Semi-supervised drug embedding using VAE in hyperbolic space.
result The method accurately places drugs in a hierarchy and predicts side-effects.

The paper introduces an adjacency constraint to improve goal-conditioned HRL.

problem Training inefficiency in goal-conditioned HRL due to large action space.
method Restricting the high-level action space to a k-step adjacent region of the current state.
result The adjacency constraint preserves optimal hierarchical policies and improves HRL performance.

An important problem in multi-label classification is to capture label patterns or underlying structures that have an impact on such patterns. This paper addresses one such problem, namely how to exploit hierarchical structures over labels. We present a novel method to learn vector representations of a label space give…

2014-12-22abs ↗pdf ↗

Sparse model for noisy datasets using hierarchical regularization.

problem Learning from large noisy datasets with sparse representations.
method Hierarchical learning strategy with projection-based penalty operators.
result Efficient sparse model reconstruction and generalizability on real datasets.