arXiv research

The paper classifies compact homogeneous Finsler manifolds with positive flag curvature.

Paper classifies pseudomanifolds over stratified spaces.

Current techniques in machine learning are so far are unable to learn classifiers that are robust to adversarial perturbations. However, they are able to learn non-robust classifiers with very high accuracy, even in the presence of random perturbations. Towards explaining this gap, we highlight the hypothesis that $\te…

Recent works on adversarial perturbations show that there is an inherent trade-off between standard test accuracy and adversarial accuracy. Specifically, they show that no classifier can simultaneously be robust to adversarial perturbations and achieve high standard test accuracy. However, this is contrary to the stand…

Enhances mixture models with classifier-defined weights.

Authors classify 3D locally standard T-pseudomanifolds under weaker conditions.

HET-XL improves heteroscedastic classifiers for large-scale image classification.

We show that there may exist an inherent tension between the goal of adversarial robustness and that of standard generalization. Specifically, training robust models may not only be more resource-consuming, but also lead to a reduction of standard accuracy. We demonstrate that this trade-off between the standard accura…

Improved conformal prediction for better conditional coverage of classifier predictions.

Suppose some classifiers are selected from a set of hypothesis classifiers to form an equally-weighted ensemble that selects a member classifier at random for each input example. Then the ensemble has an error bound consisting of the average error bound for the member classifiers, a term for selectivity that varies fro…

It is shown that Legendrian (resp. transverse) cable links in the 3-sphere with its standard tight contact structure, i.e. links consisting of an unknot and a cable of that unknot, are classified by their oriented link type and the classical invariants (Thurston-Bennequin invariant and rotation number in the Legendrian…

We investigate the automatic classification of patient discharge notes into standard disease labels. We find that Convolutional Neural Networks with Attention outperform previous algorithms used in this task, and suggest further areas for improvement.

The paper classifies homomorphisms between braid groups and mapping class groups.

The article explains how to estimate confusion matrices for classifiers using unlabeled data.

We propose to reinterpret a standard discriminative classifier of p(y|x) as an energy based model for the joint distribution p(x,y). In this setting, the standard class probabilities can be easily computed as well as unnormalized values of p(x) and p(x|y). Within this framework, standard discriminative architectures ma…

This work introduces significativity indices for agreement values between classifiers.

Classifiers based on probabilistic graphical models are very effective. In continuous domains, maximum likelihood is usually used to assess the predictions of those classifiers. When data is scarce, this can easily lead to overfitting. In any probabilistic setting, Bayesian averaging (BA) provides theoretically optimal…

We classify transverse Hopf links in the standard contact 3-space up to transverse isotopy in terms of their components' self-linking number.

Classifies actions of tori on manifolds up to diffeomorphisms.

New IRT method identifies useful datasets for ML classifier evaluation.

Ensembles improve classifier performance by reducing bias, not variance.

Uniform Closure Method and Bayes classifier perform similarly in classifying open knots.

We classify the Legendrian torus knots in S^1\times S^2 with its standard tight contact structure up to Legendrian isotopy.

MALT improves adversarial attacks by targeting classes more efficiently.

Rule-based classifiers quantify uncertainty using Bernoulli random variables.

Currently, engineers at substation service providers match customer data with the corresponding internally used signal names manually. This paper proposes a machine learning method to automate this process based on substation signal mapping data from a repository of executed projects. To this end, a bagged token classi…

A classification algorithm, called the Linear Centralization Classifier (LCC), is introduced. The algorithm seeks to find a transformation that best maps instances from the feature space to a space where they concentrate towards the center of their own classes, while maximimizing the distance between class centers. We …

New framework reduces strategic manipulation cost for minority groups in fair classification.

The standard approach to supervised classification involves the minimization of a log-loss as an upper bound to the classification error. While this is a tight bound early on in the optimization, it overemphasizes the influence of incorrectly classified examples far from the decision boundary. Updating the upper bound …

Unified approach for fair classification with overlapping groups.

The paper classifies and constructs 6D GKM manifolds with 4 fixed points.

Motivated by the work of Leznov--Mostovoy, we classify the linear deformations of standard $2n$-dimensional phase space that preserve the obvious symplectic $\mathfrak{o}(n)$-symmetry. As a consequence, we describe standard phase space, as well as $T^{*}S^{n}$ and $T^{*}\mathbb{H}^{n}$ with their standard symplectic fo…

Classifies $T^k$-manifolds with continuous sections.

In this paper we establish rigorous benchmarks for image classifier robustness. Our first benchmark, ImageNet-C, standardizes and expands the corruption robustness topic, while showing which classifiers are preferable in safety-critical applications. Then we propose a new dataset called ImageNet-P which enables researc…

Classifies compact Clifford-Klein forms for specific Lie algebras.

Knowing when a classifier's prediction can be trusted is useful in many applications and critical for safely using AI. While the bulk of the effort in machine learning research has been towards improving classifier performance, understanding when a classifier's predictions should and should not be trusted has received …

New depth function for partial orders helps compare machine learning algorithms.

We introduce a novel approach for training adversarial models by replacing the discriminator score with a bi-modal Gaussian distribution over the real/fake indicator variables. In order to do this, we train the Gaussian classifier to match the target bi-modal distribution implicitly through meta-adversarial training. W…

In various situations one is given only the predictions of multiple classifiers over a large unlabeled test data. This scenario raises the following questions: Without any labeled data and without any a-priori knowledge about the reliability of these different classifiers, is it possible to consistently and computation…

CbMLC improves multi-label classification with noisy labels.

The Information Bottleneck (IB) objective uses information theory to formulate a task-performance versus robustness trade-off. It has been successfully applied in the standard discriminative classification setting. We pose the question whether the IB can also be used to train generative likelihood models such as normal…

New neural network approach using mutual information.

Multi-output inference tasks, such as multi-label classification, have become increasingly important in recent years. A popular method for multi-label classification is classifier chains, in which the predictions of individual classifiers are cascaded along a chain, thus taking into account inter-label dependencies and…

Classifies fibered ribbon pretzels, except for a few cases.

Machine learning models are often susceptible to adversarial perturbations of their inputs. Even small perturbations can cause state-of-the-art classifiers with high "standard" accuracy to produce an incorrect prediction with high confidence. To better understand this phenomenon, we study adversarially robust learning …

OTF uses optimal transport to measure classifier fairness.

A simple proof is given of the following result first observed by J. Adachi: embedded circles tangent to the standard Engel structure on Euclidean 4-space are classified, up to isotopy via such embeddings, by their rotation number.

Unified approach to non-standard classification tasks.