arXiv research

New techniques solve robust principal component analysis problems.

Factor analysis provides linear factors that describe relationships between individual variables of a data set. We extend this classical formulation into linear factors that describe relationships between groups of variables, where each group represents either a set of related variables or a data set. The model also na…

A Python tool generates synthetic data for cluster analysis from high-level descriptions.

The level set tree approach of Hartigan (1975) provides a probabilistically based and highly interpretable encoding of the clustering behavior of a dataset. By representing the hierarchy of data modes as a dendrogram of the level sets of a density estimator, this approach offers many advantages for exploratory analysis…

New method for high-fidelity shape representations from raw data.

We analyze the level sets of the norm of the Witten spinor in an asymptotically flat Riemannian spin manifold of positive scalar curvature. Level sets of small area are constructed. We prove curvature estimates which quantify that, if the total mass becomes small, the manifold becomes flat with the exception of a set o…

Proposes RSP model for efficient big data analysis.

The clusters of a distribution are often defined by the connected components of a density level set. However, this definition depends on the user-specified level. We address this issue by proposing a simple, generic algorithm, which uses an almost arbitrary level set estimator to estimate the smallest level at which th…

Probe-level models have led to improved performance in microarray studies but the various sources of probe-level contamination are still poorly understood. Data-driven analysis of probe performance can be used to quantify the uncertainty in individual probes and to highlight the relative contribution of different noise…

VarFA efficiently estimates student skill levels with uncertainty for adaptive testing.

Improved adaptive rates for Lipschitz bandit problem.

Sharp volume bounds for conic 2-spheres with Gaussian curvature constraints.

LOO prediction method improves generalization guarantees for arbitrary datasets.

A new framework for discovering macro-level causes and effects from micro-level data.

The so-called level crossing analysis has been used to investigate the empirical data set. But there is a lack of interpretation for what is reflected by the level crossing results. The fractional Gaussian noise as a well-defined stochastic series could be a suitable benchmark to make the level crossing findings more s…

New method for online learning IC models with node-level feedback.

Bayesian analysis optimizes stop-loss thresholds based on drawdown distributions.

Develops methods to adjust prediction set coverage based on post-selection analysis.

The paper explores using set-level ratings for better user-item preference prediction in recommender systems.

This paper tackles multilayer graph clustering via convex layer aggregation.

New method for online meta-learning reduces dynamic regret in changing environments.

GANs generate DOOM levels similar to human-designed ones.

Metrics stabilize persistent homology in data analysis.

Introduces Motion Programs for better video analysis of human motion.

Linear Discriminant Analysis (LDA) is a well-known method for dimensionality reduction and classification. Previous studies have also extended the binary-class case into multi-classes. However, many applications, such as object detection and keyframe extraction cannot provide consistent instance-label pairs, while LDA …

High-dimensional GAN training analyzed with exact dynamics.

Study on spin random fields using chaos decomposition for cosmic microwave background modeling.

Study robust mean estimation under coordinate-level corruptions using Hamming distance.

A new algorithm improves Wasserstein discriminant analysis for better data classification.

Scalable psFA for fMRI data extracts sparse components.

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

Study uses machine learning to analyze state drug policies and reduce overdose deaths.

Constructs bivariate quantiles using vine copulas for multivariate analysis.

The level crossing and inverse statistics analysis of DAX and oil price time series are given. We determine the average frequency of positive-slope crossings, $ν_α^+$, where $T_α =1/ν_α^+$ is the average waiting time for observing the level $α$ again. We estimate the probability $P(K, α)$, which provides us the probab…

Paper analyzes churn behavior in mobile games at micro and macro levels.

Study active learning for multi-level user preferences in recommendation systems.

Estimates population mean from user-level data with privacy, accounting for heterogeneity.

New methods test correlation between network structure and node features.

A distributed SGD method for heterogeneous networks with hubs and workers.

Advocates for Marr's levels of analysis to unify machine learning debates.

New control on diameter and curvature for evolving surfaces.

The main object of study in the paper is the distance from a point to a line in the Riemannian manifold associated with the Heston model. We reduce the problem of computing such a distance to certain minimization problems for functions of one variable over finite intervals. One of the main ideas in this paper is to use…

In this paper we present a new approach to the study of asymptotically flat static metrics arising in general relativity. In the case where the static potential is bounded, we introduce new quantities which are proven to be monotone along the level set flow of the potential function. We then show how to use these prope…

Develops consistent approximations for composite optimization problems.

Unified view of monotonicity formulas for inverse mean curvature flow and $p$-capacitary potentials.

New algorithm stabilizes bi-level hyperparameter optimization.

Dynamic ensemble selection (DES) techniques work by estimating the level of competence of each classifier from a pool of classifiers. Only the most competent ones are selected to classify a given test sample. Hence, the key issue in DES is the criterion used to estimate the level of competence of the classifiers in pre…

A key problem in statistical modeling is model selection, how to choose a model at an appropriate level of complexity. This problem appears in many settings, most prominently in choosing the number ofclusters in mixture models or the number of factors in factor analysis. In this tutorial we describe Bayesian nonparamet…