arXiv research

Non-convex SGD learns halfspaces with adversarial label noise efficiently.

We carefully study how well minimizing convex surrogate loss functions, corresponds to minimizing the misclassification error rate for the problem of binary classification with linear predictors. In particular, we show that amongst all convex surrogate losses, the hinge loss gives essentially the best possible bound, o…

We address the problem of learning to benchmark the best achievable classifier performance. In this problem the objective is to establish statistically consistent estimates of the Bayes misclassification error rate without having to learn a Bayes-optimal classifier. Our learning to benchmark framework improves on previ…

A new method for high-dimensional data classification reduces misclassification errors.

This work aims to reduce inexplicable errors in deep neural networks by obtaining class-level semantics and penalizing misclassifications.

The misclassification error distance and the adjusted Rand index are two of the most commonly used criteria to evaluate the performance of clustering algorithms. This paper provides an in-depth comparison of the two criteria, aimed to better understand exactly what they measure, their properties and their differences. …

The paper analyzes classification algorithms on Korobov space and derives learning rates.

Unsupervised classification methods learn a discriminative classifier from unlabeled data, which has been proven to be an effective way of simultaneously clustering the data and training a classifier from the data. Various unsupervised classification methods obtain appealing results by the classifiers learned in an uns…

Unified framework for cost-sensitive ensemble learning.

We study the misclassification error for community detection in general heterogeneous stochastic block models (SBM) with noisy or partial label information. We establish a connection between the misclassification rate and the notion of minimum energy on the local neighborhood of the SBM. We develop an optimally weighte…

Bayesian method reduces misclassification errors in ranking Pareto-optimal solutions.

New algorithm reduces misclassification costs in neural networks.

Develops probabilistic safety regions for scalable classifiers.

This paper proposes CSADA to make DNNs cost-sensitive.

Despite having excellent performances for a wide variety of tasks, modern neural networks are unable to provide a reliable confidence value allowing to detect misclassifications. This limitation is at the heart of what is known as an adversarial example, where the network provides a wrong prediction associated with a s…

Minimizes indecisions in selective classification to control misclassification rates.

We analyze the problem of learning a single user's preferences in an active learning setting, sequentially and adaptively querying the user over a finite time horizon. Learning is conducted via choice-based queries, where the user selects her preferred option among a small subset of offered alternatives. These queries …

Unlike traditional programs (such as operating systems or word processors) which have large amounts of code, machine learning tasks use programs with relatively small amounts of code (written in machine learning libraries), but voluminous amounts of data. Just like developers of traditional programs debug errors in the…

Study on error probability for classification of heavy-tailed renewal processes.

Automated data-driven decision making systems are increasingly being used to assist, or even replace humans in many settings. These systems function by learning from historical decisions, often taken by humans. In order to maximize the utility of these systems (or, classifiers), their training involves minimizing the e…

Polynomial-time tester-learner for general halfspaces with Gaussian adversarial noise.

Boosting algorithm reduces error in noisy data.

Optimal subset selection for hypothesis testing with penalties.

Optimizes active learning for machine learning models with Bayesian approach.

New research shows logistic regression can achieve optimal error rate for agnostic learning of halfspaces.

Study identifies and mitigates causes of image misclassifications in CNN models.

We identify spectral conditions for reliable neural probe interpretation.

The study sets limits on how well halfspaces can be learned when labels are corrupted.

A novel method for classification with rejection using ensemble of cost-sensitive classifiers.

Subspace models play an important role in a wide range of signal processing tasks, and this paper explores how the pairwise geometry of subspaces influences the probability of misclassification. When the mismatch between the signal and the model is vanishingly small, the probability of misclassification is determined b…

New method compresses large sample data for faster discriminant analysis.

Study improves theoretical understanding of Bayesian deep learning for classification tasks.

Proposes a novel SVM model for binary classification with different misclassification costs.

PANDA improves linear discriminant analysis in high dimensions with minimal tuning.

The paper studies how to use AI-generated labels in econometrics to avoid bias.

In epidemiology, identifying the effect of exposure variables in relation to a time-to-event outcome is a classical research area of practical importance. Incorporating propensity score in the Cox regression model, as a measure to control for confounding, has certain advantages when outcome is rare. However, in situati…

We study the problem of {\em distribution-independent} PAC learning of halfspaces in the presence of Massart noise. Specifically, we are given a set of labeled examples $(\mathbf{x}, y)$ drawn from a distribution $\mathcal{D}$ on $\mathbb{R}^{d+1}$ such that the marginal distribution on the unlabeled points $\mathbf{x}…

We propose an empirical Bayes estimator based on Dirichlet process mixture model for estimating the sparse normalized mean difference, which could be directly applied to the high dimensional linear classification. In theory, we build a bridge to connect the estimation error of the mean difference and the misclassificat…

Paper introduces a new uncertainty measure for misclassification detection.

Study shows BNN inference accelerators are vulnerable to soft errors, causing significant misclassification.

This work investigates square loss in overparametrized neural networks, revealing its advantages in robustness and calibration.

Develops NPMC method for noisy labels, improving multiclass classification accuracy.

The paper analyzes the maximum margin algorithm's performance on noisy data.

In his seminal work, Schapire (1990) proved that weak classifiers could be improved to achieve arbitrarily high accuracy, but he never implied that a simple majority-vote mechanism could always do the trick. By comparing the asymptotic misclassification error of the majority-vote classifier with the average individual …

Convolutional neural networks handle rotated image symmetries without dimensionality issues.

In many machine learning applications, crowdsourcing has become the primary means for label collection. In this paper, we study the optimal error rate for aggregating labels provided by a set of non-expert workers. Under the classic Dawid-Skene model, we establish matching upper and lower bounds with an exact exponent …

A new framework selects information sources to test hypotheses robustly, even with misclassifications.

Efficient algorithm for CLSBM reduces misclassification rate.