arXiv research

MPVAE learns latent embeddings and label correlations for multi-label classification.

MTHetGNN models complex relations in multivariate time series forecasting.

OracleAD detects multivariate time series anomalies without labels.

The paper monitors artificial neural networks using embeddings and multivariate control charts.

We in this paper propose a realizable framework TECU, which embeds task-specific strategies into update schemes of coordinate descent, for optimizing multivariate non-convex problems with coupled objective functions. On one hand, TECU is capable of improving algorithm efficiencies through embedding productive numerical…

We prove a central limit theorem for the components of the eigenvectors corresponding to the $d$ largest eigenvalues of the normalized Laplacian matrix of a finite dimensional random dot product graph. As a corollary, we show that for stochastic blockmodel graphs, the rows of the spectral embedding of the normalized La…

Paper develops heavy-tailed embeddings for better text classification and augmentation.

Proposes a new model for online anomaly detection in multivariate time series.

M-CaStLe discovers causal structures in multivariate space-time data.

Study develops advanced models to forecast complex LOB data.

Paper generalizes kernel mean embedding to von Neumann-algebra-valued measures.

We introduce a model for causal structure learning from multivariate functional data, even when graphs have cycles.

Two strategies for embedding new data points from proximity data are explored.

New distances for comparing multivariate normal distributions.

A new metric space model for point process excitations uncovers hidden interactions.

A criterion for training-free time-lagged spectral embeddings of multivariate time series

Study delta invariant of curves on rational surfaces using topological methods.

New algorithm extracts shared latent space for cortico-muscular interactions.

Overcomplete representations and dictionary learning algorithms kept attracting a growing interest in the machine learning community. This paper addresses the emerging problem of comparing multivariate overcomplete representations. Despite a recurrent need to rely on a distance for learning or assessing multivariate ov…

A new approach selects tuning parameters for embedding methods.

Time series constitute a challenging data type for machine learning algorithms, due to their highly variable lengths and sparse labeling in practice. In this paper, we tackle this challenge by proposing an unsupervised method to learn universal embeddings of time series. Unlike previous works, it is scalable with respe…

Paper tackles class-incremental time series classification with dual-stream feature extraction.

New framework for calculating multivariate risk measures using Wishart process.

Delay embedding---a method for reconstructing dynamical systems by delay coordinates---is widely used to forecast nonlinear time series as a model-free approach. When multivariate time series are observed, several existing frameworks can be applied to yield a single forecast combining multiple forecasts derived from va…

New methods explain NE embeddings by identifying key variables.

MTS-CycleGAN adapts multivariate time series data for ironmaking industry.

How can we effectively encode evolving information over dynamic graphs into low-dimensional representations? In this paper, we propose DyRep, an inductive deep representation learning framework that learns a set of functions to efficiently produce low-dimensional node embeddings that evolves over time. The learned embe…

We present a self-contained proof of the Gauss-Bonnet theorem for two-dimensional surfaces embedded in $R^3$ using just classical vector calculus. The exposition should be accessible to advanced undergraduate and non-expert graduate students. It may be viewed as an illustration and exercise in multivariate calculus and…

This paper provides an algorithm for simulating improper (or noncircular) complex-valued stationary Gaussian processes. The technique utilizes recently developed methods for multivariate Gaussian processes from the circulant embedding literature. The method can be performed in $\mathcal{O}(n\log_2 n)$ operations, where…

Wide Boosting improves GB's performance on multivariate output tasks.

Scientists in many fields have the common and basic need of dimensionality reduction: visualizing the underlying structure of the massive multivariate data in a low-dimensional space. However, many dimensionality reduction methods confront the so-called "crowding problem" that clusters tend to overlap with each other i…

This paper connects functional data analysis with machine learning techniques.

Given a transverse knot $K$ in a three dimensional contact manifold $(Y,α)$, in [13] Colin, Ghiggini, Honda and Hutchings define a hat version of embedded contact homology for $K$, that we call $\widehat{ECK}(K,Y,α)$, and conjecture that it is isomorphic to the knot Floer homology $\widehat{HFK}(K,Y)$. We define here a…

Small neural networks embed arbitrary metric spaces into Gaussian mixtures.

Calibrating a Lévy process usually requires characterizing its jump distribution. Traditionally this problem can be solved with nonparametric estimation using the empirical characteristic functions (ECF), assuming certain regularity, and results to date are mostly in 1D. For multivariate Lévy processes and less smooth …

We present a new paradigm for speeding up randomized computations of several frequently used functions in machine learning. In particular, our paradigm can be applied for improving computations of kernels based on random embeddings. Above that, the presented framework covers multivariate randomized functions. As a bypr…

Sensor data analysis plays a key role in health assessment of critical equipment. Such data are multivariate and exhibit nonlinear relationships. This paper describes how one can exploit nonlinear dimension reduction techniques, such as the t-distributed stochastic neighbor embedding (t-SNE) and kernel principal compon…

New framework analyzes pre-stock jump trading behaviors using multivariate time series analysis.

Accurately determining dependency structure is critical to discovering a system's causal organization. We recently showed that the transfer entropy fails in a key aspect of this---measuring information flow---due to its conflation of dyadic and polyadic relationships. We extend this observation to demonstrate that this…

Unified normative modeling for neuroimaging phenotypes using denoising diffusion models.

Timer-XL predicts multidimensional time series using a unified Transformer approach.

CoIFNet unifies imputation and forecasting for robust multivariate time series prediction with missing values.

Visual analytics system for comparing medical records using sequence embeddings.

This paper presents a novel time series clustering method, the self-organising eigenspace map (SOEM), based on a generalisation of the well-known self-organising feature map (SOFM). The SOEM operates on the eigenspaces of the embedded covariance structures of time series which are related directly to modes in those tim…

Improves supervised learning with target-embedding autoencoders.

Accurately learning from user data while providing quantifiable privacy guarantees provides an opportunity to build better ML models while maintaining user trust. This paper presents a formal approach to carrying out privacy preserving text perturbation using the notion of dx-privacy designed to achieve geo-indistingui…

Based on a faithful representation of the heavy tail multivariate distribution of asset returns introduced previously (Sornette et al., 1998, 1999) that we extend to the case of asymmetric return distributions, we generalize the return-risk efficient frontier concept to incorporate the dimensions of large risks embedde…

PCA simplifies multivariate extreme data analysis.