arXiv research

UNTIE learns representations of coupled categorical data.

The paper shows how integrating categorical semantics can enhance unsupervised domain translation.

Discrete-AIR model identifies objects in images with interpretable latent codes.

InfoCatVAE learns disentangled representations for categorical data.

Categorical bundles provide a natural framework for gauge theories involving multiple gauge groups. Unlike the case of traditional bundles there are distinct notions of triviality, and hence also of local triviality, for categorical bundles. We study categorical principal bundles that are product bundles in the categor…

Improves BO methods for categorical and integer-valued variables.

Local-HDP learns independent topics for each 3D object category in real-time.

Paper improves video categorization using temporal coherence.

A new, efficient $k$-modes algorithm improves clustering of categorical data.

Spectral clustering adapted for mixed data types without preprocessing.

Develops methods for clustering hypergraphs with categorical edge labels.

Study extends cognitive modeling to natural images, revealing the importance of image representation.

New algorithm for clustering categorical data without using distance measures.

Develops a binomial model in categorical probability spaces.

Involutive Hopf monoids yield surface invariants.

In this paper we present a method for learning a discriminative classifier from unlabeled or partially labeled data. Our approach is based on an objective function that trades-off mutual information between observed examples and their predicted categorical class distribution, against robustness of the classifier to an …

A new method for categorical variational inference using discrete normalizing flows.

We define the thin fundamental categorical group ${\mathcal P}_2(M,*)$ of a based smooth manifold $(M,*)$ as the categorical group whose objects are rank-1 homotopy classes of based loops on $M$, and whose morphisms are rank-2 homotopy classes of homotopies between based loops on $M$. Here two maps are rank-$n$ homotop…

A new model for supervised learning to rank using gradient estimation.

New approach categorizes objective functions for embodied agents.

CatFlow uses variational flow matching for efficient graph generation.

New unsupervised learning framework for sound recognition.

VAIOM models financial returns using continuous input and categorical output.

Paper proposes PP-GCN for fine-grained social event categorization.

VCML learns concepts and metaconcepts from images and questions.

SCOPE fuses categorical variable levels to estimate high-dimensional linear models.

This work defines a categorical notion of principal bundles.

New optimization algorithm for mixed-variable problems improves efficiency.

Simplified approach to Galois theories in category theory.

The trace of the affine Hecke category is compared with the elliptic Hall algebra.

Develops a new theory of localization in algebraic geometry.

New method interprets object representations from human behavior.

Fine-grained visual categorization (FGVC) is to categorize objects into subordinate classes instead of basic classes. One major challenge in FGVC is the co-occurrence of two issues: 1) many subordinate classes are highly correlated and are difficult to distinguish, and 2) there exists the large intra-class variation (e…

A new method for optimizing functions with both categorical and continuous variables.

A scalable algorithm compresses large categorical feature vocabularies while maximizing mutual information.

This paper addresses image classification through learning a compact and discriminative dictionary efficiently. Given a structured dictionary with each atom (columns in the dictionary matrix) related to some label, we propose cross-label suppression constraint to enlarge the difference among representations for differe…

We give completely combinatorial proofs of the main results of [3] using polygons. Namely, we prove that the mapping class group of a surface with boundary acts faithfully on a finitely-generated linear category. Along the way we prove some foundational results regarding the relevant objects from bordered Heegaard Floe…

This work tackles robust optimization with multiple objectives for structural design.

Feature selection problems arise in a variety of applications, such as microarray analysis, clinical prediction, text categorization, image classification and face recognition, multi-label learning, and classification of internet traffic. Among the various classes of methods, forward feature selection methods based on …

People can learn complex visual concepts from just a few examples.

The paper defines and studies the category of Z-graded manifolds, including their intrinsic structure and formal properties.

A method for diffusion on probability simplex for generative models.

A new method for generative modeling of discrete data using geometric latent subspaces.

Designs a framework to transfer causal models between similar environments.

DMTG groups tasks for multi-task learning in one shot.

New framework uses cohomology to analyze probabilistic distortions and arbitrage.

Unified discrete diffusion for categorical data simplifies training and sampling.

We reformulate superalgebra and supergeometry in completely categorical terms by a consequent use of the functor of points. The increased abstraction of this approach is rewarded by a number of great advantages. First, we show that one can extend supergeometry completely naturally to infinite-dimensional contexts. Seco…