arXiv research

New method calibrates reference distributions for bounded support.

Connects robust optimization to conformal prediction for uncertainty sets.

Proposes a method to estimate acceptance regions for many classes, including new ones.

Proposes a text perturbation method using a Mahalanobis metric to balance privacy and utility.

The paper develops a theory for speculative decoding acceptance criteria.

The article improves the display of acceptable exchange ratios for merging companies.

Develops a method for stress testing correlations of financial portfolios.

This paper presents a general notion of Mahalanobis distance for functional data that extends the classical multivariate concept to situations where the observed data are points belonging to curves generated by a stochastic process. More precisely, a new semi-distance for functional observations that generalize the usu…

Boosts kernel two-sample test power with multiple kernels.

Flexible classifier using Mahalanobis distances for non-elliptical distributions.

Extends Mahalanobis distance to Banach spaces for anomaly detection.

Mahalanobis distance detects anomalies well, but not for classification.

A method uses Shapley values and Mahalanobis distances to explain multivariate outliers.

ECPv2 optimizes Lipschitz functions efficiently and scalably.

The paper connects neural networks to Mahalanobis distance for interpretability.

Compressing data helps learn Mahalanobis metrics effectively.

Learning Mahalanobis metric spaces is an important problem that has found numerous applications. Several algorithms have been designed for this problem, including Information Theoretic Metric Learning (ITML) [Davis et al. 2007] and Large Margin Nearest Neighbor (LMNN) classification [Weinberger and Saul 2009]. We study…

Clustering and classification critically rely on distance metrics that provide meaningful comparisons between data points. We present mixed-integer optimization approaches to find optimal distance metrics that generalize the Mahalanobis metric extensively studied in the literature. Additionally, we generalize and impro…

Enhances forecasting of complex systems using FKMD.

We propose a low-rank approach to learning a Mahalanobis metric from data. Inspired by the recent geometric mean metric learning (GMML) algorithm, we propose a low-rank variant of the algorithm. This allows to jointly learn a low-dimensional subspace where the data reside and the Mahalanobis metric that appropriately f…

Previous work shows that adversarially robust generalization requires larger sample complexity, and the same dataset, e.g., CIFAR-10, which enables good standard accuracy may not suffice to train robust models. Since collecting new training data could be costly, we focus on better utilizing the given data by inducing t…

The study proposes a framework to accept OOD data based on competence scores.

Timely detection of abrupt anomalies is crucial for real-time monitoring and security of modern systems producing high-dimensional data. With this goal, we propose effective and scalable algorithms. Proposed algorithms are nonparametric as both the nominal and anomalous multivariate data distributions are assumed unkno…

Feedforward neural networks with random hidden nodes suffer from a problem with the generation of random weights and biases as these are difficult to set optimally to obtain a good projection space. Typically, random parameters are drawn from an interval which is fixed before or adapted during the learning process. Due…

Bayesian nonparametric models improve OOD detection, especially with complex covariance structures.

For many tasks and data types, there are natural transformations to which the data should be invariant or insensitive. For instance, in visual recognition, natural images should be insensitive to rotation and translation. This requirement and its implications have been important in many machine learning applications, a…

A visualization aids in comparing regression models by highlighting errors and correlations.

This paper learns user preferences from comparisons using Mahalanobis metrics.

NUTS mixing time scales as d^(1/4) for Gaussian distributions.

Proposes ridge regression on Riemannian manifolds for time-series prediction.

Study robustness of early-stopping GD for linear regression attacks.

This paper quantifies how hard it is to identify specific data points in machine learning models.

New method combines neural networks with Monte Carlo for complex system reliability.

Develops a computationally tractable differentially private mean estimator called the balloon mean.

2L-FUSE enhances feature sparsity through kernel learning.

New star-shaped acceptability indexes generalize existing methods.

We analyze the cumulative distribution of total personal income of USA counties, and gross domestic product of Brazilian, German and United Kingdom counties, and also of world countries. We verify that generalized exponential distributions, related to nonextensive statistical mechanics, describe almost the whole spectr…

We derive a new radial link for binary classification under shared elliptical distributions.

Studies acceptable bundles on a partially punctured polydisk.

A new algorithm estimates mean adaptively to covariance, faster and more flexible than existing methods.

Study on acceptable bundles on a punctured disk.

Biometrics emerged as a robust solution for security systems. However, given the dissemination of biometric applications, criminals are developing techniques to circumvent them by simulating physical or behavioral traits of legal users (spoofing attacks). Despite face being a promising characteristic due to its univers…

A new test validates ensemble models against the null hypothesis.

Simple conditions for comonotonic additive risk measures from acceptance sets.

Single particle reconstruction (SPR) from cryo-electron microscopy (EM) is a technique in which the 3D structure of a molecule needs to be determined from its contrast transfer function (CTF) affected, noisy 2D projection images taken at unknown viewing directions. One of the main challenges in cryo-EM is the typically…

A new algorithm reduces online exp-concave optimization runtime.

Kernel functions in support vector machines (SVM) are needed to assess the similarity of input samples in order to classify these samples, for instance. Besides standard kernels such as Gaussian (i.e., radial basis function, RBF) or polynomial kernels, there are also specific kernels tailored to consider structure in t…

In this paper we present a theoretical framework for studying coherent acceptability indices in a dynamic setup. We study dynamic coherent acceptability indices and dynamic coherent risk measures, and we establish a duality between them. We derive a representation theorem for dynamic coherent risk measures in terms of …