arXiv research

Maps sets to probability distributions to minimize information loss.

New framework infers multiple classes per image for one-shot learning.

We prove that every proper $n$-dimensional length metric space admits an "approximate isometric embedding" into Lorentzian space $\mathbb{R}^{3n+6,1}$. By an "approximate isometric embedding" we mean an embedding which preserves the energy functional on a prescribed set of geodesics connecting a dense set of points.

This paper finds a linear relationship between t-SNE perplexity and data set size.

Analytic sets with unique infinite tangent cone are algebraic.

Continuous MDS embeds sequences of dissimilarities in Euclidean space.

Smoothly approximates embeddings in Lorentzian manifolds.

New lower bounds on embedding dimensions for neural network architectures.

The paper extends a link criterion for Lipschitz normal embeddings to definable sets in o-minimal structures.

New tool: relative Hopf invariant for Poincaré surgery.

Study on quantum particle evolution on Grushin cylinder, embedding in R^3.

New faster, space-saving methods for subspace embeddings in tensors.

Word embeddings are a popular approach to unsupervised learning of word relationships that are widely used in natural language processing. In this article, we present a new set of embeddings for medical concepts learned using an extremely large collection of multimodal medical data. Leaning on recent theoretical insigh…

We solve the vector embedding problem by minimizing total distortion under constraints.

In this paper two zero-dimensional compact sets with equal topological and fractal dimensions but embedded in Euclidean space by different ways are under study. Diffraction of plane electromagnetic wave propagated and reflected by fractal surfaces is considered for each of these compact sets placed in vacuum. It is obt…

A {\it wrinkled embedding} $f:V^n\to W^m$ is a topological embedding which is a smooth embedding everywhere on $V$ except a set of $(n-1)$-dimensional spheres, where $f$ has cuspidal corners. In this paper we prove that any rotation of the tangent plane field $TV\subset TW$ of a {\it smoothly embedded} submanifold $V\s…

Bi-Lipschitz mappings can embed certain algebraic sets into high-dimensional spaces.

We study the problem of isometrically embedding a two-dimensional Riemannian manifold into Euclidean three-space. It is shown that if Gaussian curvature vanishes to finite order and its zero set consists of two smooth curves tangent at a point, then local sufficiently smooth isometric embedding exists.

Fewer obstructions for small graphs in knotless embedding.

Ensembling word embeddings to improve distributed word representations has shown good success for natural language processing tasks in recent years. These approaches either carry out straightforward mathematical operations over a set of vectors or use unsupervised learning to find a lower-dimensional representation. Th…

We describe a new method called t-ETE for finding a low-dimensional embedding of a set of objects in Euclidean space. We formulate the embedding problem as a joint ranking problem over a set of triplets, where each triplet captures the relative similarities between three objects in the set. By exploiting recent advance…

The paper provides concentration bounds for embeddings of generative models.

New invariant metrics preserved under deformed Markov embeddings.

The paper examines the consistency of item embeddings in recommendation systems.

FCA2VEC embeds formal concept analysis data for large datasets.

We examine doing probabilistic descent over manifolds implicitly defined by a set of polynomials with rational coefficients. The system of polynomials is assumed to be triangularized. An application of Whitney's embedding theorem allows us to work in a reduced dimensional embedding space. A numerical continuation metho…

Typical graph embeddings may not capture type-specific bipartite graph features that arise in such areas as recommender systems, data visualization, and drug discovery. Machine learning methods utilized in these applications would be better served with specialized embedding techniques. We propose two embeddings for bip…

The paper establishes concentration bounds for embeddings of generative models.

The paper introduces a method for detecting principal communities and embedding vertices.

BERT embeddings improve sequence quality metrics.

There is a well-known way to describe a link diagram as a (signed) plane graph, called its Tait graph. This concept was recently extended, providing a way to associate a set of embedded graphs (or ribbon graphs) to a link diagram. While every plane graph arises as a Tait graph of a unique link diagram, not every embedd…

Introduces PELP for graph-enhanced word embeddings.

TransINT embeds KGs by preserving implication rules, outperforming existing methods.

We establish a correspondence between the dimer model on a bipartite graph and a circle pattern with the combinatorics of that graph, which holds for graphs that are either planar or embedded on the torus. The set of positive face weights on the graph gives a set of global coordinates on the space of circle patterns wi…

This paper improves topic modeling by embedding words and topics together.

Arnlind, Hoppe and Huisken showed how to express the Gauss and mean curvature of a surface embedded in a Riemannian manifold in terms of Poisson brackets of the embedding coordinates. We generalize these expressions to the pseudo-Riemannian setting and derive explicit formulas for the case of surfaces embedded in $\R^m…

Given a small corpus $\mathcal D_T$ pertaining to a limited set of focused topics, our goal is to train embeddings that accurately capture the sense of words in the topic in spite of the limited size of $\mathcal D_T$. These embeddings may be used in various tasks involving $\mathcal D_T$. A popular strategy in limited…

New learning rates for embeddings in RKHSs, even when the target is not Hilbert-Schmidt.

New method for fair influence maximization in social networks.

Probabilistic hash embeddings improve online learning of categorical features.

SANNE model generates embeddings for unseen nodes in graph networks.

This paper proposes an out-of-sample extension framework for a global manifold learning algorithm (Isomap) that uses temporal information in out-of-sample points in order to make the embedding more robust to noise and artifacts. Given a set of noise-free training data and its embedding, the proposed framework extends t…

The purpose of this paper is to present, for all $n\ge 3$, very simple examples of continuous maps $f:M^{n-1} \to M^{n}$ from closed $(n-1)$-manifolds $M^{n-1}$ into closed $n$-manifold $M^n$ such that even though the singular set $S(f)$ of $f$ is countable and dense, the map $f$ can nevertheless be approximated by an …

Transformers encode latent distributions in text, improving performance in out-of-distribution cases.

Extends coisotropic embedding theorem to various geometric settings.

Given a finite or infinite planar graph all of whose faces have degree 4, we study embeddings in the plane in which all edges have length 1, that is, in which every face is a rhombus. We give a necessary and sufficient condition for the existence of such an embedding, as well as a description of the set of all such emb…

A new approach selects tuning parameters for embedding methods.

We obtain estimations for isotopy classes of embeddings of closed k-connected n-manifolds into R^{2n-k-1} for n>2k+5 and k\ge0. This is done in terms of an exact sequence involving the Whitney invariants and an explicitly constructed action of H_{k+1}(N;Z_2) on the set of embeddings. (For k\ne1 classification results w…