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.
LNPE enhances local connections in embeddings using extended neighbor propagation.
Neighbor embeddings balance attraction and repulsion to visualize data.
New methods explain NE embeddings by identifying key variables.
Acoustic Neighbor Embeddings map speech and text to fixed dimensions for phonetic confusability.
Explains SNE, t-SNE, and their variants for manifold learning.
Improves visualization of high-dimensional data by correcting misleading artifacts in neighbor embedding methods.
Unified view of SOMs and SNE from a common framework.
Stochastic Neighbor Embedding and its variants are widely used dimensionality reduction techniques -- despite their popularity, no theoretical results are known. We prove that the optimal SNE embedding of well-separated clusters from high dimensions to any Euclidean space R^d manages to successfully separate the cluste…
NE-VAE prevents posterior collapse in VAEs by embedding neighbors in latent space.
Proposes MR-SNE for multimodal data visualization.
p-SNE embeds Poisson count data into low dimensions preserving structure.
Manifold learning now plays a very important role in machine learning and many relevant applications. Although its superior performance in dealing with nonlinear data distribution, data sparsity is always a thorny knot. There are few researches to well handle it in manifold learning. In this paper, we propose Hierarchi…
Recently manifold learning algorithm for dimensionality reduction attracts more and more interests, and various linear and nonlinear, global and local algorithms are proposed. The key step of manifold learning algorithm is the neighboring region selection. However, so far for the references we know, few of which propos…
Locally-contextual CRFs improve sequence labeling performance.
Framework predicts patient risk progression over time.
Improves time series classification with forest proximities.
Heterophily affects GNN robustness; separating ego- and neighbor-embeddings improves defense.
New method uses MHN for associative learning in network embedding.
GICDM corrects hubness in embedding spaces for better generative model evaluation.
Graph node embedding aims at learning a vector representation for all nodes given a graph. It is a central problem in many machine learning tasks (e.g., node classification, recommendation, community detection). The key problem in graph node embedding lies in how to define the dependence to neighbors. Existing approach…
DSNE visualizes data velocity in lower dimensions.
New methods use vector search and nearest-neighbor matching for policy learning in causal inference.
The t-distributed Stochastic Neighbor Embedding (t-SNE) is a powerful and popular method for visualizing high-dimensional data. It minimizes the Kullback-Leibler (KL) divergence between the original and embedded data distributions. In this work, we propose extending this method to other f-divergences. We analytically a…
NESS improves neighbor embedding for smooth cell-state transitions in single-cell data.
Paper studies t-SNE convergence with generalized kernels.
The distance metric plays an important role in nearest neighbor (NN) classification. Usually the Euclidean distance metric is assumed or a Mahalanobis distance metric is optimized to improve the NN performance. In this paper, we study the problem of embedding arbitrary metric spaces into a Euclidean space with the goal…
We study the problem of object detection over scanned images of scientific documents. We consider images that contain objects of varying aspect ratios and sizes and range from coarse elements such as tables and figures to fine elements such as equations and section headers. We find that current object detectors fail to…
This paper proves the manifold hypothesis for lower embedding dimensions using osculating hyperspheres.
Proposes a boundary detection method inspired by LLE for high-dimensional data.
Revised ct-SNE improves t-SNE for visualizing data beyond labels.
Social recommendation has emerged to leverage social connections among users for predicting users' unknown preferences, which could alleviate the data sparsity issue in collaborative filtering based recommendation. Early approaches relied on utilizing each user's first-order social neighbors' interests for better user …
Word embedding, which encodes words into vectors, is an important starting point in natural language processing and commonly used in many text-based machine learning tasks. However, in most current word embedding approaches, the similarity in embedding space is not optimized in the learning. In this paper we propose a …
The local linear embedding algorithm (LLE) is a non-linear dimension-reducing technique, widely used due to its computational simplicity and intuitive approach. LLE first linearly reconstructs each input point from its nearest neighbors and then preserves these neighborhood relations in the low-dimensional embedding. W…
New method for computing terminal embeddings in sublinear time.
Improved multi-task averaging reduces mean squared error in high-dimensional data.
In this paper, we focus on learning low-dimensional embeddings for nodes in graph-structured data. To achieve this, we propose Caps2NE -- a new unsupervised embedding model leveraging a network of two capsule layers. Caps2NE induces a routing process to aggregate feature vectors of context neighbors of a given target n…
GTEA learns node representations in temporal interaction graphs.
We propose a method for recognizing moving vehicles, using data from roadside audio sensors. This problem has applications ranging widely, from traffic analysis to surveillance. We extract a frequency signature from the audio signal using a short-time Fourier transform, and treat each time window as an individual data …
Estimates missing distributions using nearest neighbors with kernel methods.
Stochastic neighbor embedding (SNE) and related nonlinear manifold learning algorithms achieve high-quality low-dimensional representations of similarity data, but are notoriously slow to train. We propose a generic formulation of embedding algorithms that includes SNE and other existing algorithms, and study their rel…
MCE reduces embedding instability in nonlinear dimensionality reduction.
In the advent of big data era, interactive visualization of large data sets consisting of M*10^5+ high-dimensional feature vectors of length N (N ~ 10^3+), is an indispensable tool for data exploratory analysis. The state-of-the-art data embedding (DE) methods of N-D data into 2-D (3-D) visually perceptible space (e.g.…
Among the extensions of twin support vector machine (TSVM), some scholars have utilized K-nearest neighbor (KNN) graph to enhance TSVM's classification accuracy. However, these KNN-based TSVM classifiers have two major issues such as high computational cost and overfitting. In order to address these issues, this paper …
End-to-end deep metric learning tackles multi-label image classification.
DANCE improves prediction set efficiency for deep learning models.
We consider the problem of embedding unweighted, directed k-nearest neighbor graphs in low-dimensional Euclidean space. The k-nearest neighbors of each vertex provides ordinal information on the distances between points, but not the distances themselves. We use this ordinal information along with the low-dimensionality…
We study intersection of two polyhedral spheres without self-intersections in 3-space. We find necessary and sufficient conditions on sequences x = x_1,x_2,...,x_n, y = y_1,y_2,...,y_n of positive integers, for existence of 2-dimensional polyhedra f,g in R^3 homeomorphic to the sphere and such that * f-g has n connecte…
Cyber-Physical Systems (CPSs) have been pervasive including smart grid, autonomous automobile systems, medical monitoring, process control systems, robotics systems, and automatic pilot avionics. As usually implemented on embedded devices, CPS is typically constrained by computation capacity and energy consumption. In …