In image classification, visual separability between different object categories is highly uneven, and some categories are more difficult to distinguish than others. Such difficult categories demand more dedicated classifiers. However, existing deep convolutional neural networks (CNN) are trained as flat N-way classifi…
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.
169,051 papers · 148 categories
Trend · papers per month
48 results for “Large Categories”
New coarse LS-category introduced for groups and spaces.
problem Large-scale topological properties of groups and spaces.
method Introducing a coarse analog of Lusternik-Schnirelmann category for metric spaces.
result Established lower and upper bounds for geometrically finite and bicombable groups.
New skein categories for non-semisimple settings, extending existing theory.
problem Extending skein theory to non-semisimple settings.
method Introducing skein categories based on tensor ideals in linear ribbon categories.
result Skein categories coincide with factorization homology in non-semisimple settings.
We improve stochastic gradient estimators for large categories using Rao-Blackwellization.
problem Computing gradients over large or infinite categories.
method Rao-Blackwellization to reduce variance of stochastic gradient estimators.
result Improves performance on semi-supervised classification and pixel attention tasks.
Pareto index induced from the scale of companiesphysics.soc-ph
Employing profits data of Japanese companies in 2002 and 2003, we confirm that Pareto's law and the Pareto index are derived from the law of detailed balance and Gibrat's law. The last two laws are observed beyond the region where Pareto's law holds. By classifying companies into job categories, we find that companies …
We define the notion of a Kirby element of a ribbon category C (not necessarily semisimple). Kirby elements lead to 3-manifolds invariants. We characterize (in terms of the structure maps of some categorical Hopf algebra) a set of Kirby elements of C which is sufficiently large to recover the known quantum invariants c…
A nonparametric framework for inferring orders of categorical data from category-real ordered pairsstat.ME
Framework orders categories and measures differences from real data.
problem Inferring orders and differences between categories.
method Nonparametric Estimation statistics framework.
result Scalable framework for large datasets.
Dimension zero at all scalesmath.MG
We consider the notion of dimension in four categories: the category of (unbounded) separable metric spaces and (metrically proper) Lipschitz maps, and the category of (unbounded) separable metric spaces and (metrically proper) uniform maps. A unified treatment is given to the large scale dimension and the small scale …
This is a large audience version of our previous work (see math.AG/0301146) in which we prove the existence of an (exact) equivalence between the category of coherent analytic sheaves and the category of -coherent sheaves. We also include here the complete proof of our main Theorem.
MILCCI integrates labels across categories for better understanding of multi-trial data.
problem Understanding how labels encode multi-trial observations and disentangling their effects.
method Sparse per-trial decomposition leveraging label similarities within each category.
result MILCCI identifies interpretable components and integrates label information.
An important question with a rich history is the extent to which the symplectic category is larger than the Kaehler category. Many interesting examples of non-Kaehler symplectic manifolds have been constructed. However, sufficiently large symmetries can force a symplectic manifold to be Kaehler. In this paper, we solve…
To the best of our knowledge, this paper presents the first large-scale study that tests whether network categories (e.g., social networks vs. web graphs) are distinguishable from one another (using both categories of real-world networks and synthetic graphs). A classification accuracy of was achieved using a …
We consider the problem of personalization of online services from the viewpoint of ad targeting, where we seek to find the best ad categories to be shown to each user, resulting in improved user experience and increased advertisers' revenue. We propose to address this problem as a task of ranking the ad categories dep…
Model reconstructs novel 3D shapes with a single prior image.
problem Generalizing single-view 3D reconstruction to new classes with limited data.
method Reframes reconstruction as refinement of a provided prior shape.
result Model reconstructs novel classes with limited training data.
As a promising area in artificial intelligence, a new learning paradigm, called Small Sample Learning (SSL), has been attracting prominent research attention in the recent years. In this paper, we aim to present a survey to comprehensively introduce the current techniques proposed on this topic. Specifically, current S…
This study improves cryptocurrency price forecasting using time series categorization and deep learning.
problem Accurate prediction of cryptocurrency prices is challenging due to limited data and diverse behaviors.
method The approach involves categorizing financial time series, creating deep learning models for each category, and combining data from other cryptocurrencies to increase training data.
result The method increases prediction accuracy by learning each subseries category with similar behavior and combining data from other cryptocurrencies.
Verification determines whether two samples belong to the same class or not, and has important applications such as face and fingerprint verification, where thousands or millions of categories are present but each category has scarce labeled examples, presenting two major challenges for existing deep learning models. W…
Frobenius extensions play a central role in the link homology theories based upon the sl(n) link variants, and each of these Frobenius extensions may be recast geometrically via a category of marked cobordisms in the manner of Bar-Natan. Here we explore a large family of such marked cobordism categories that are releva…
New Frank-Wolfe algorithm speeds up SVM-type multi-category learning.
problem Improving pattern recognition performance in multi-category SVM learning.
method Developed a new optimization algorithm based on Frank-Wolfe framework for MC-SVM variants.
result Closed-form solutions for direction finding and line search in the Frank-Wolfe framework for MC-SVM.
DSNC learns binary codes for multi-class classification with sublinear inference.
problem High inference complexity in one-vs-all methods for large multi-class classification.
method DSNC learns binary codes and mappings end-to-end without a priori tuning.
result DSNC achieves sublinear inference complexity and outperforms baselines.
The study finds that the export shares of machinery and food/crude materials are significantly correlated with GDP.
problem Understanding the relationship between export shares and GDP across different commodity sectors.
method Analysis of GDP and international trade data using the SITC classification from 1962 to 2000.
result The export shares of machinery and food/crude materials are significantly correlated with GDP, following a power-law relationship.
Two-stage neural network for few-shot image recognition.
problem Few-shot image recognition for novel categories.
method Multi-layer neural network with feature extraction and classification stages.
result Competitive performance on four standard datasets.
The metric Rips filtration, universal quasigeodesic cones, and hierarchically hyperbolic spacesmath.MG
Develops a new framework for large-scale geometry.
problem Characterizing large-scale models of metric spaces.
method Categorical framework for metric Rips filtration and universal quasigeodesic cones.
result Establishes universal properties and adjointness of the Rips colimit.
The Lipshitz-Sarkar stable homotopy link invariant defines Steenrod squares on the Khovanov cohomology of a link. Lipshitz-Sarkar constructed an algorithm for computing the first two Steenrod squares. We develop a new algorithm which implements the flow category simplification techniques previously defined by the autho…
We discuss the equivalence between the categories of certain ribbon graphs and subgroups of the modular group and use it to construct exponentially large families of not Hurwitz equivalent simple braid monodromy factorizations of the same element. As an application, we also obtain exponentially large families of {\…
Robotic clothing manipulation improved with fashion image analysis techniques.
problem Automated identification of clothing categories and landmarks for robotic tasks.
method Training data augmentation methods and rotation invariant convolutions.
result Our approach outperforms state-of-the-art models on unseen datasets.
Studies amenable category's monotonicity and its relation to topological complexity.
problem Monotonicity of amenable category for degree-one maps.
method Uses amenable covers and compares with topological complexity.
result Establishes a relation between amenable category and topological complexity.
Formal Contact Categoriesmath.GT
To each oriented surface S, we associate a differential graded category Ko(S). The homotopy category Ho(Ko(S)) is a triangulated category which satisfies properties akin to those of the contact categories studied by K. Honda. These categories are also related to the algebraic contact categories of Y. Tian and to the bo…
New method constructs tilings of the plane using directed edges and alignments.
problem Modeling tilings of the Euclidean or hyperbolic plane as presheaves over categories.
method Introducing finite categories for polygons with labeled directed edges, constructing reflective alignments.
result Characterizing alignments of tilings by comparing edge directions and generating families with elegant symmetry.
We consider the task of one-shot learning of visual categories. In this paper we explore a Bayesian procedure for updating a pretrained convnet to classify a novel image category for which data is limited. We decompose this convnet into a fixed feature extractor and softmax classifier. We assume that the target weights…
Innovative 2-categories create 4-manifold invariants.
problem Constructing invariants for 4-manifolds.
method Semisimple 2-categories, fusion 2-categories, and state-sum construction.
result Construct a state-sum invariant for 4-manifolds.
Unified framework connects deformation theory and derived categories for multiparameter persistence.
problem Algebraic complexity of multiparameter persistence modules hinders classification, stability, and interpretability.
method Combines deformation theory and derived categories to study multiparameter persistence geometrically.
result Unified conjecture relating interleaving distance to derived convolution metrics established.
Formulates a new connection between topological and geometric categories.
problem No specific problem stated; focuses on category formulation.
method Formulates a connection between a topological and geometric category.
result Provides a more precise and improved version of a previous proposal.
Local-HDP learns independent topics for each 3D object category in real-time.
problem Learning independent topics for each 3D object category in real-time.
method Local-Hierarchical Dirichlet Process (Local-HDP) with online variational inference.
result Local-HDP outperforms other approaches in accuracy, scalability, and memory efficiency.
We continue the program of structural differential geometry that begins with the notion of a tangent category, an axiomatization of structural aspects of the tangent functor on the category of smooth manifolds. In classical geometry, having an affine structure on a manifold is equivalent to having a flat torsion-free c…
Vectorizing string entries for data processing on tables: when are larger language models better?stat.ML
New research shows larger language models improve data processing for diverse entries.
problem Optimizing data processing for tables with diverse string entries.
method Analytical tasks on tables with varying language model sizes and a fuzzy join benchmark.
result Larger language models improve data processing for diverse entries, but fine-tuning is necessary.
Survey on decorated marked surfaces for Calabi-Yau categories.
problem Understanding Calabi-Yau categories and related structures.
method Introducing decorations on marked surfaces to study various categories.
result Exploration of Calabi-Yau-2 and 3 categories, braid groups, quadratic differentials, and stability conditions.
The paper defines new TQFTs from non-semisimple categories and proves spherical categories are chromatic.
problem Defining non-compact TQFTs from non-semisimple categories.
method Introducing admissible skein modules, chromatic categories, and using Juhász's cobordism presentation.
result Non-compact (2+1)-TQFTs can be defined from chromatic categories, extending Turaev-Viro TQFTs.
Unified view on big bang singularities from initial data.
problem Understanding quiescent big bang singularities from initial data.
method Unified geometric perspective on various results.
result Solutions of Oude Groeniger et al. induce data on the singularity.
Automatic selection of eye tracking variables in visual categorization in adults and infantsq-bio.QM
Automated method selects eye tracking variables for categorization tasks.
problem Limited duration of infant cooperation and biases in handpicked eye tracking variables.
method Automated selection of eye tracking variables using statistical techniques.
result Same eye tracking variables classify category learners from non-learners in adults and infants with high accuracy.
Spider category comparison proves equivalence to Sikora's quotient category.
problem Comparing skein theories of .
method Proved equivalence between spider category and Sikora's quotient category.
result Spider category is equivalent to Sikora's quotient category.
The study finds conditions for nonmaximal topological complexity of manifolds with abelian fundamental groups.
problem Conditions for nonmaximal topological complexity of manifolds with abelian fundamental groups.
method Analyzes conditions and examples to generalize results on topological complexity and Lusternik-Schnirelmann category.
result Generalizes results on topological complexity and Lusternik-Schnirelmann category for manifolds with abelian fundamental groups.
Categorifies quantum invariants using cobordism categories and operads.
problem Categorify quantum invariants using cobordism categories and operads.
method Constructs a cobordism category with a colored operad action, categorifies quantum invariants.
result Consistency of the cobordism category and explicit functor to matrix factorizations conjectured.
ETQFTs created from non-semisimple modular categories.
problem Constructing ETQFTs from non-semisimple modular categories.
method Explicitly identify linear categories and functors in the image of ETQFTs constructed from modular categories.
result The circle category of ETQFTs is equivalent to the full subcategory of projective objects of the underlying modular category, which need not be semisimple.
We generalize the notion of monetary value measures developed with category theory in [Adachi, 2014] by extending their base category from the category \c{hi} to the category of probability spaces Prob introduced in [Adachi and Ryu, 2016].
Studies modules over a category of Jacobi diagrams in handlebodies.
problem Understanding modules over a specific category of Jacobi diagrams.
method Generalizes adjunctions and studies subquotient modules.
result Generalizes adjunctions between modules and Casimir Lie algebra modules.
Comparative Smootheologymath.DG
We compare various different definitions of "the category of smooth objects". The definitions compared are due to Chen, Frölicher, Sikorski, Smith, and Souriau. The method of comparison is to construct functors between the categories that enable us to see how the categories relate to each other. This produces a diagram…
In this article we construct Lagrangian torus fibrations for general quintic \cy hypersurfaces near the large complex limit and their mirror manifolds using gradient flow method. Then we prove the Strominger-Yau-Zaslow mirror conjecture for this class of \cy manifolds in symplectic category.