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.

168,657 papers · 148 categories

Trend · papers per month

94188281375 · Jun 202019922001200920172026
48 results for Class hierarchy

Study identifies pitfalls in assessing hierarchies for multi-class classification.

problem Lack of understanding in selecting hierarchies for multi-class classification.
method Analyzed and compared popular approaches to extracting hierarchies.
result Hierarchy quality becomes irrelevant when using powerful classifiers.

ProHOC detects OOD samples in class hierarchies, predicting them to correct internal nodes.

problem Binary OOD detection ignores semantic relationships between OOD and ID classes.
method Probabilistic hierarchical model using multi-depth networks trained for ID classification.
result ProHOC effectively classifies OOD samples to their correct internal nodes in class hierarchies.

Paper investigates methods to improve classification by inducing a hierarchy from flat labels.

problem Improving classification performance on datasets lacking a natural hierarchy.
method The approach involves clustering conditional distributions and using a hierarchical classifier with the induced hierarchy.
result The methods can discover latent hierarchies and improve accuracy in various applications.

We observe that the modular class of a Poisson-Nijhenhuis manifold has a canonical representative and that, under a cohomological assumption, this vector field is bi-hamiltonian. In many examples the associated hierarchy of flows reproduces classical integrable hierarchies.

2006-07-30abs ↗pdf ↗

New integrable deformations for topological hierarchies from Frobenius manifolds.

problem Integrable deformations of topological hierarchies from Frobenius manifolds.
method Construction of integrable deformations with polynomial tau-structures.
result Conjecture of universal object for Riemann--Hopf hierarchy.

This work improves metric learning models by incorporating class hierarchies.

problem Class hierarchies are often ignored in classification-based metric learning models.
method Trained softmax classifier and metric learning models with predefined class hierarchies.
result ProxyDR model performs better in hierarchical inference and hierarchy-informed performance.

New hierarchies derived from KP hierarchy using non-formal operators and Yang-Mills action.

problem Formal solutions of KP hierarchy and their non-formal counterparts.
method Developed new hierarchies of non-linear equations on non-formal pseudo-differential operators.
result Expressed one hierarchy as Yang-Mills action minimization.

A relation between the Goldstein-Petrich hierarchy for plane curves and the Toda lattice hierarchy is investigated. A representation formula for plane curves is given in terms of a special class of ττ-functions of the Toda lattice hierarchy. A representation formula for discretized plane curves is also discussed.

2013-10-26abs ↗pdf ↗

C-HMCNN(h) improves HMC classification by leveraging class hierarchy.

problem Hierarchical multi-label classification with class hierarchy constraints.
method Exploits class hierarchy to produce coherent predictions for multi-label classification.
result C-HMCNN(h) outperforms state-of-the-art models in HMC classification.

Legendre transformations link related integrable hierarchies.

problem Understanding relationships between integrable hierarchies.
method Legendre-type transformations of generalized Frobenius manifolds.
result Linear reciprocal transformations link related hierarchies.

Twisted UU- and twisted U/KU/K-hierarchies are soliton hierarchies introduced by Terng to find higher flows of the generalized sine-Gordon equation. Twisted O(J,J)O(J)×O(J)\frac {O(J,J)}{O(J)\times O(J)}-hierarchies are among the most important classes of twisted hierarchies. In this paper, interesting first and higher flows of twi…

2011-03-31abs ↗pdf ↗

The modular vector field of a Poisson-Nijenhuis Lie algebroid AA is defined and we prove that, in case of non-degeneracy, this vector field defines a hierarchy of bi-Hamiltonian AA-vector fields. This hierarchy covers an integrable hierarchy on the base manifold, which may not have a Poisson-Nijenhuis structure.

2007-01-17abs ↗pdf ↗

We propose an extension of the differential system for constant mean curvature (CMC) surfaces in a three dimensional space form to an associated hierarchy of evolution equations by the higher-order commuting symmetries. The infinite sequence of higher-order conservation laws of CMC surfaces admit the corresponding exte…

2013-12-27abs ↗pdf ↗

Proves existence and uniqueness of loop equation solutions for semisimple Frobenius manifolds.

problem Existence and uniqueness of solutions to loop equations in generalized Frobenius manifolds.
method Proves existence and uniqueness of solutions to loop equations for semisimple generalized Frobenius manifolds.
result Existence and uniqueness of solutions to loop equations for semisimple generalized Frobenius manifolds.

Kropholler's class of groups is the smallest class of groups which contains all finite groups and is closed under the following operator: whenever GG admits a finite-dimensional contractible GG-CW-complex in which all stabilizer groups are in the class, then GG is itself in the class. Kropholler's class admits a hie…

2009-08-25abs ↗pdf ↗

We propose an extension of the structure equation for constant mean curvature (CMC) surfaces in a three dimensional Riemannian space form to the associated CMC hierarchy of evolution equations by the higher-order commuting symmetries. Via the canonical formal Killing field, considered as an infinitely prolonged and loo…

2014-09-23abs ↗pdf ↗

We generalize the Toda lattice hierarchy by considering N+M dependent variables. We construct roots and logarithms of the Lax operator which are uniquely defined operators with coefficients that are εε-series of differential polynomials in the dependent variables, and we use them to provide a Lax pair definition of th…

2006-04-11abs ↗pdf ↗

Paper tackles many-class few-shot learning with class hierarchy, improving accuracy.

problem Many-class few-shot learning problem in practical applications.
method Leverages class hierarchy to train a coarse-to-fine classifier using memory-augmented hierarchical-classification network (MahiNet).
result MahiNet outperforms state-of-the-art models on MCFS problems in both supervised and meta-learning settings.

New method optimizes hierarchical multi-label classification results.

problem Optimizing classification results respecting class hierarchy and classifier scores.
method Introducing CATCH objective function and mLPR metric to rank multi-label classification results.
result HierRank algorithm optimizes CATCH, improving decision accuracy.

Deep networks learn hierarchical data by invariant representations.

problem How many examples are needed for deep networks to learn hierarchical data?
method Random Hierarchy Model: synthetic tasks inspired by language and images hierarchy.
result Deep networks learn by invariant representations and require a detectable number of correlations between low-level features and classes.

Enhances image classification by integrating semantic hierarchy into CNN models.

problem Limited use of external guidance in image classification.
method Integrates label-hierarchy knowledge into CNN-based classifiers and uses order-preserving embeddings.
result Boosts image classification performance through semantic hierarchy integration.

HCC extends conformal prediction to handle class hierarchies, improving prediction reliability.

problem Uncertainty quantification in classification models with class hierarchy considerations.
method Formulates HCC as a constrained optimization problem, ensuring coverage guarantees with a smaller subset of candidate solutions.
result HCC produces more reliable prediction sets by leveraging class hierarchy information.

New hierarchies and equations derived from Poisson structures.

problem Development of new hierarchies and equations from Poisson structures.
method Introduction and classification of multicomponent Poisson structures, derivation of hierarchies and equations.
result New Harry Dym and Hunter-Saxton equations derived for arbitrary number of components.

The thesis introduces methods to use semantic hierarchy in image classification.

problem Limited work in training image classifiers with non-conventional external guidance.
method Injects label hierarchy knowledge into arbitrary classifiers and uses order-preserving embeddings for image classification.
result Both embedding-based models and CNN-classifiers with hierarchical information outperform a hierarchy-agnostic model.

Constructs integrable hierarchies for generalized Frobenius manifolds with non-flat unity.

problem Integrable hierarchies for generalized Frobenius manifolds with non-flat unity.
method Constructs a bihamiltonian integrable hierarchy of hydrodynamic type.
result Integrable hierarchy possesses Virasoro symmetries and a tau structure.

This paper develops a cohomological hierarchy for bistable visual paradoxes.

problem Understanding the hierarchy of visual paradoxes built from bistable elements.
method Develops a cohomological hierarchy using Z2\mathbb{Z}_2 coefficients and a discrete Stokes theorem.
result Reveals a hierarchy of paradox classes from H0H^0 through H2H^2, refined at each degree by the relative/absolute distinction.

Efficient algorithm for evaluating hierarchical classification methods at multiple operating points.

problem Evaluating hierarchical classification methods at multiple operating points.
method Efficient algorithm to produce operating characteristic curves for any method that assigns scores to every class in the hierarchy.
result Top-down classifiers are dominated by a naive flat softmax classifier across the entire operating range.

The study quantifies the information needed for causal queries at different levels of Pearl's hierarchy.

problem How much additional information is needed for interventional and counterfactual queries compared to observational queries?
method Formalized via query-class description length, using Kolmogorov complexity of answer oracles induced by SCMs.
result Binary acyclic SCMs show a quadratic gap between observational and interventional descriptions, and a logarithmic gap between interventional and counterfactual descriptions.

New method improves blackbox attack transferability by perturbing feature hierarchy.

problem Improving transferability of blackbox attacks across different models and datasets.
method Perturbs representations throughout feature hierarchy to mimic other classes.
result Achieves 10x increase in targeted success rate compared to other methods.

A new hierarchy quantifies agency in systems based on information processing.

problem Lack of a measurable, universal definition for agency in intelligent systems.
method Developed a bottom-up framework based on information processing hierarchy.
result Identified three orders of information processing (I, II, III) as necessary for agency.

Paper proposes integrating hierarchical class structure into prototypical network supervision.

problem Improving classification accuracy in tasks with hierarchical class structures.
method Integrates hierarchical class structure (metric) into prototypical network supervision.
result Consistent improvement of error rate weighted by the cost matrix compared to traditional methods.

We define a hierarchy of special classes of constrained Willmore surfaces by means of the existence of a polynomial conserved quantity of some type, filtered by an integer. Type 1 with parallel top term characterises parallel mean curvature surfaces and, in codimension 1, type 1 characterises constant mean curvature su…

2015-07-05abs ↗pdf ↗

We propose a formally completely integrable extension of heat hierarchy based on the space of symmetries isomorphic to the Weyl algebra A1\mathcal{A}_1. The extended heat hierarchy will be the basic model for the analysis of the extension of KP hierarchy, and other integrable equations.

2014-01-19abs ↗pdf ↗

Wise's Quasiconvex Hierarchy Theorem classifying hyperbolic virtually compact special groups in terms of quasiconvex hierarchies played an essential role in Agol's proof of the Virtual Haken Conjecture. Answering a question of Wise, we construct a new virtual quasiconvex hierarchy for relatively hyperbolic virtually co…

2019-03-28abs ↗pdf ↗

Symmetry reduction of Painlevé IV to Flaschka-Newell Painlevé II

problem Isomonodromic deformation problem associated with rank-two meromorphic connections
method Symmetry Ψ(λ)=σ1Ψ(λ)σ1Ψ(-λ)= σ_1 Ψ(λ) σ_1
result Induced isomonodromic dynamics coincides with Flaschka-Newell Painlevé II hierarchy

Scroll structures on solutions of 4D integrable equations are involutive and governed by a dispersionless hierarchy.

problem Characterizing the geometry of solutions to 4D integrable equations.
method Defining rational normal scrolls and showing their involutivity.
result Involutive scroll structures are governed by a dispersionless integrable hierarchy.

Constructs tri-Hamiltonian structure and Frobenius manifold for asymmetric gAL hierarchy

problem Tri-Hamiltonian structure and Frobenius manifold for asymmetric gAL hierarchy
method Local tri-Hamiltonian structure construction and Frobenius manifold construction
result Dispersionless limits of flows belong to Principal Hierarchy

We introduce two families of soliton hierarchies: the twisted hierarchies associated to symmetric spaces. The Lax pairs of these two hierarchies are Laurent polynomials in the spectral variable. Our constructions gives a hierarchy of commuting flows for the generalized sine-Gordon equation (GSGE), which is the Gauss-Co…

2010-10-27abs ↗pdf ↗