Minimal dimensions found for flag manifolds embeddings.
problem Finding the smallest dimensions for flag manifolds embeddings.
method Equivariant embeddings of orthogonal and unitary groups acting on real and complex flag manifolds.
result Minimal dimensions achieved at isospectral models.
We create interpretable word embeddings through sparse coding.
problem Difficult to interpret word embeddings in natural language processing.
method Transform pretrained dense word embeddings into sparse embeddings through sparse coding.
result Sparse embeddings are more interpretable and achieve good performance.
Paper shows graphs can be embedded in lower dimensions than expected.
problem Choosing the right embedding dimension for graph analysis.
method Utilizes hidden manifold structure to predict lower-dimensional embedding.
result Graphs can be embedded in much lower dimensions than previously thought.
We study piecewise linear co-dimension two embeddings of closed oriented manifolds in Euclidean space, and show that any such embedding can always be isotoped to be a closed braid as long as the ambient dimension is at most five, extending results of Alexander (in ambient dimension three), and Viro and independently Ka…
Sparse OSEs achieve optimal embedding dimension of O(d).
problem Achieving optimal embedding dimension for sparse OSEs.
method Random sparsified matrix with m≥(1+θ)d non-zeros per column. result Sparse OSEs can achieve embedding dimension m=O(d), improving on previous m=O(dlog(d)). We give a fast oblivious L2-embedding of A∈Rnxd to B∈Rrxd satisfying (1−ε)∥Ax∥22≤∥Bx∥22<=(1+ε)∥Ax∥22. Our embedding dimension r equals d, a constant independent of the distortion ε. We use as a black-box any L2-embedding $Π…
New lower bounds on embedding dimensions for neural network architectures.
problem Ensuring neural networks can handle symmetries like permutations in high dimensions.
method Novel technique to prove lower bounds on embedding dimensions.
result Proves new lower bounds on embedding dimensions for Deep Sets and Janossy pooling.
New algorithm reduces sketching dimension to effective problem size.
problem Solving L2-regularized least-squares problems efficiently.
method Randomized algorithm using Gaussian and SRHT embeddings.
result Preserves convergence guarantees with reduced embedding dimension.
Any closed, connected Riemannian manifold M can be smoothly embedded by its Laplacian eigenfunction maps into Rm for some m. We call the smallest such m the maximal embedding dimension of M. We show that the maximal embedding dimension of M is bounded from above by a constant depending only on the…
Embedding representations power machine intelligence in many applications, including recommendation systems, but they are space intensive -- potentially occupying hundreds of gigabytes in large-scale settings. To help manage this outsized memory consumption, we explore mixed dimension embeddings, an embedding layer arc…
AEALT uses autoencoders to reduce text embedding dimensions for improved efficiency.
problem High dimensionality of text embeddings hinders downstream tasks.
method Factor-augmented supervised learning with autoencoders.
result AEALT outperforms conventional deep-learning approaches.
Proves open Riemann surfaces can be embedded into 4D space.
problem Embedding open Riemann surfaces in lower dimensions.
method Proper harmonic embedding by harmonic functions.
result Reduces embedding dimension from previously known 5D to 4D.
Recommendation problems with large numbers of discrete items, such as products, webpages, or videos, are ubiquitous in the technology industry. Deep neural networks are being increasingly used for these recommendation problems. These models use embeddings to represent discrete items as continuous vectors, and the vocab…
This work shows dimension regularization can replace skip-gram negative sampling for graph embeddings, improving efficiency and performance.
problem Efficiently enforcing dissimilarity among node embeddings in graph learning.
method Dimension regularization as an alternative to skip-gram negative sampling.
result Dimension regularization is a more efficient approach to enforcing dissimilarity in graph embeddings.
Compact reachability embeddings for hierarchical data
problem Computing geometric representations of hierarchical data
method Using embeddings to represent hierarchies
result Proven compact embeddings for directed trees and graphs of treewidth
SFBoW provides sentence embeddings with predefined dimensions.
problem Sentence embeddings problem at document-level.
method Refinement of Fuzzy Bag-of-Words, predefined dimension.
result Competitive performances in Semantic Textual Similarity benchmarks.
This work improves understanding of dimension reduction algorithms and their probabilistic embeddings.
problem Improving theoretical understanding of non-linear dimension reduction algorithms.
method Analytical investigation of a generalized multidimensional scaling optimization problem.
result Probabilistic formulation of the problem leads to deterministic embeddings, contrary to standard implementations.
Study proves higher-order conformal forms don't exist in odd dimensions.
problem Proving non-existence of higher-order conformal forms in odd dimensions.
method Analyzing conformal hypersurface embeddings and differential order invariants.
result General non-existence of higher-order conformal forms in odd dimensions.
DSNE visualizes data velocity in lower dimensions.
problem Understanding movement patterns in high-dimensional data.
method DSNE is a variation of Stochastic Neighbor Embedding that learns velocity embeddings using Euclidean distances on a unit sphere.
result DSNE enables visualization of data movement in lower dimensions.
Maps on surfaces can be embedded into spheres with minimal dimensions.
problem Embedding periodic maps of surfaces into spheres with the smallest possible dimensions.
method Determining the minimal dimensions m for embeddings of periodic maps of order n on surfaces of genus g into spheres Sm. result For each integer k>1, there exist infinitely many periodic maps such that the smallest possible m is equal to k. Solves embedding problem for 5D manifolds into Calabi-Yau 3-folds.
problem Embedding a 5D manifold into a Calabi-Yau 3-fold with a specific 3-form.
method Defines 'strongly pseudoconvex' 3-forms and shows solvability of embedding problem for these forms under certain conditions.
result Perturbative embedding problem can be solved for closed strongly pseudoconvex 3-forms if a vector space of obstructions vanishes.
POLAR framework interprets word embeddings using polar opposites.
problem Lack of interpretability in pre-trained word embeddings.
method Adopt semantic differentials and polar opposites to transform embeddings.
result Interpretable word embeddings maintain performance comparable to original embeddings.
Embed spherical quandles into Lie groups smoothly.
problem Embedding spherical quandles into Lie groups.
method Construct smooth embeddings into conjugation quandles of Lie groups.
result Embeddings into orthogonal, Spin, or Pin groups in dimensions 1 and 3 compared with Bergman and Akita's.
The Whitney embedding theorem gives an upper bound on the smallest embedding dimension of a manifold. If a data set lies on a manifold, a random projection into this reduced dimension will retain the manifold structure. Here we present an algorithm to find a projection that distorts the data as little as possible.
MEDAL converts manifold embeddings into models for rigorous validation.
problem Challenges in validating manifold embeddings without held-out validation.
method Develops MEDAL framework that distills embeddings into autoencoder models.
result Enables rigorous validation of manifold embeddings and hyperparameters.
Study on embedding properties of Riemannian manifolds with specific geometric constraints.
problem Embedding Riemannian manifolds with certain geometric properties into Euclidean spaces.
method Utilizing a known trick to find embeddings with specific dimensions.
result Existence of isometric embeddings with specified dimensions for Riemannian manifolds.
Minimal equivariant embedding found for flag manifolds.
problem Finding the smallest possible dimension for equivariant embeddings of flag manifolds.
method Proved the smallest possible dimension (n−1)(n+2)/2 for SOn(R)-equivariant embeddings of Flag(k1,…,kp,Rn). result The smallest possible dimension (n−1)(n+2)/2 is the optimal for SOn(R)-equivariant embeddings of Flag(k1,…,kp,Rn). We seek to better understand the difference in quality of the several publicly released embeddings. We propose several tasks that help to distinguish the characteristics of different embeddings. Our evaluation of sentiment polarity and synonym/antonym relations shows that embeddings are able to capture surprisingly nua…
The paper shows how coarse embeddings affect homological Dehn functions.
problem Characterizing groups with coarse embeddings into hyperbolic groups.
method Demonstrates a coarse embedding theorem for homological filling functions.
result Characterizes groups with coarse embeddings into hyperbolic groups of geometric dimension 2.
Given a closed polygon P having n edges, embedded in R^d, we give upper and lower bounds for the minimal number of triangles t needed to form a triangulated PL surface in R^d having P as its geometric boundary. The most interesting case is dimension 3, where the polygon may be knotted. We use the Seifert suface constru…
We prove that every visual Gromov hyperbolic space X whose boundary at infinity has the finite capacity dimension n admits a quasi-isometric embedding into (n+1)-fold product of metric trees.
We discuss a variation of Gromov's notion of asymptotic dimension that was introduced and named Nagata dimension by Assouad. The Nagata dimension turns out to be a quasisymmetry invariant of metric spaces. The class of metric spaces with finite Nagata dimension includes in particular all doubling spaces, metric trees, …
The study shows how to accurately estimate embedding vectors in high dimensions.
problem How to accurately estimate embedding vectors in high-dimensional spaces.
method A simple probability model and a variant of low-rank approximate message passing (AMP) method.
result The AMP approach enables precise predictions of the accuracy of the estimation in certain high-dimensional limits.
Estimates for graph embeddings into symmetric spaces derived from coarse geometry.
problem Estimating optimal volume of graph embeddings into symmetric spaces.
method Coarse geometric thick embeddings and wiring techniques.
result Optimal and lower bounds for graph embeddings in symmetric spaces of different ranks.
t-SNE is a popular tool for embedding multi-dimensional datasets into two or three dimensions. However, it has a large computational cost, especially when the input data has many dimensions. Many use t-SNE to embed the output of a neural network, which is generally of much lower dimension than the original data. This l…
Hyperbolic embeddings offer excellent quality with few dimensions when embedding hierarchical data structures like synonym or type hierarchies. Given a tree, we give a combinatorial construction that embeds the tree in hyperbolic space with arbitrarily low distortion without using optimization. On WordNet, our combinat…
This work improves tensor decomposition methods, especially for large datasets.
problem Lack of efficient methods for estimating Tucker decompositions.
method Applies Johnson-Lindenstrauss type guarantees to Tucker decompositions with random embeddings.
result Effective dimension reduction with minimal error for large tensors.
We examine the algebraic and geometric properties of a uni-directional GRU and word embeddings trained end-to-end on a text classification task. A hyperparameter search over word embedding dimension, GRU hidden dimension, and a linear combination of the GRU outputs is performed. We conclude that words naturally embed t…
In this work, we contribute a new multi-layer neural network architecture named ONCF to perform collaborative filtering. The idea is to use an outer product to explicitly model the pairwise correlations between the dimensions of the embedding space. In contrast to existing neural recommender models that combine user em…
We prove that any compact almost complex manifold (M,J) of real dimension 2m admits a pseudo-holomorphic embedding in a Euclidean space of dimension 4m+2, endowed with a suitable non-standard almost complex structure. Moreover, we give a necessary and sufficient condition, expressed in terms of the Segre class…
Acoustic Neighbor Embeddings map speech and text to fixed dimensions for phonetic confusability.
problem Mapping speech and text to fixed dimensions for phonetic confusability.
method Adapting SNE to sequential inputs, training two encoder neural networks.
result More accurate results with low-dimensional embeddings in word recognition tasks.
Minimal sphere dimension for equivariant embedding of circles.
problem Embedding a bouquet of circles into a sphere.
method Finding the minimal dimension of the sphere for equivariant embedding.
result The minimal dimension is 2g−1. The paper establishes a continuous embedding between two types of Barron spaces in neural networks.
problem Understanding the relationship between two types of Barron spaces in neural networks.
method Introduced a continuous embedding inequality between Barron and spectral Barron spaces.
result The embedding inequality holds for any function in the spaces, with constants independent of the input dimension.
Minimal simplicial complexes in high dimensions always contain complex links.
problem Existence of complex links in high-dimensional embeddings.
method Demonstrated through minimal simplicial complexes in R2n. result Minimal simplicial n-complexes inevitably contain a nonsplittable two-component link. We prove a structural theorem that provides a precise local picture of how a sequence of closed embedded minimal hypersurfaces with uniformly bounded index (and volume if the ambient dimension is greater than three) in a Riemannian manifold of dimension at most seven, can degenerate. Loosely speaking, our results show …
Word embedding models have become a fundamental component in a wide range of Natural Language Processing (NLP) applications. However, embeddings trained on human-generated corpora have been demonstrated to inherit strong gender stereotypes that reflect social constructs. To address this concern, in this paper, we propo…
Tubes in manifolds require wide spaces.
problem Embedding constraints in Riemannian manifolds.
method Analyzing uniformly thick tubular neighborhoods.
result Conditions for manifold embeddings with wide tubes.
Investigates neural codes and their embeddings, proving conjectures and introducing new code types.
problem Analyzing neural codes and their embedding dimensions.
method Combinatorial, topological, and algebraic analysis; proving conjectures; introducing new neural code types.
result Proves conjectures about neural codes and their embeddings, introduces new code types.