arXiv research

Characterizes distribution-free rates in unbalanced classification problems.

Optimal classification rules control error rates in multiclass mixture models.

Study controls error rates of binary classifiers using hypothesis testing.

Paper bounds convergence rate of adversarial surrogate risk.

Paper improves classification rates for private data.

Near-Exponential Convergence Rates for kNN Classification

Study optimal rates for multiclass classification, resolving open questions.

Paper establishes a universal growth rate for smooth surrogate losses in classification.

Algorithm minimizes risk for multiclass classification of stochastic diffusion paths.

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

New formula classifies product reviews into higher and lower ratings based on sentiment analysis.

Unified framework for comparing classification metrics across different imbalance rates.

Convolutional neural networks improve image classification accuracy.

Study shows exponential error reduction in multiclass classification without bias-variance trade-off.

We investigate the problem of classification in the presence of unknown class-conditional label noise in which the labels observed by the learner have been corrupted with some unknown class dependent probability. In order to obtain finite sample rates, previous approaches to classification with unknown class-conditiona…

Study derives error decay rates for kernel classification under source and capacity conditions.

This paper tackles worst-class error rate in classification tasks.

This paper studies universal rates of ERM for binary classification under agnostic learning.

Study expands multiclass classification models with new rates and partial concept classes.

New bounds on majority voting's accuracy for multi-class classification problems.

We consider stochastic gradient descent and its averaging variant for binary classification problems in a reproducing kernel Hilbert space. In the traditional analysis using a consistency property of loss functions, it is known that the expected classification error converges more slowly than the expected risk even whe…

The paper establishes convergence rates for MoE models in classification problems.

Theory extends optimal learning rates without realizability assumption.

Study on CNNs' learning rates and approximation capacities.

Paper shows SVM can achieve super fast convergence rates.

Deep neural networks achieve optimal learning rates for high-dimensional classification.

New algorithm for adaptive experimental design in scientific settings.

Nearest neighbor methods are a popular class of nonparametric estimators with several desirable properties, such as adaptivity to different distance scales in different regions of space. Prior work on convergence rates for nearest neighbor classification has not fully reflected these subtle properties. We analyze the b…

New method uses public data to achieve optimal nonparametric classification with privacy constraints.

Paper assesses error estimates of Random Forests classification.

A method for making predictions with a reject option using conformal prediction.

New loss function improves convergence rate for neural networks.

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

As known, attribute selection is a method that is used before the classification of data mining. In this study, a new data set has been created by using attributes expressing overall satisfaction in Turkey Statistical Institute (TSI) Life Satisfaction Survey dataset. Attributes are sorted by Ranking search method using…

Neural networks can approximate high-dimensional classifiers with ReLU networks under margin conditions.

Let $\cF$ be a set of $M$ classification procedures with values in $[-1,1]$. Given a loss function, we want to construct a procedure which mimics at the best possible rate the best procedure in $\cF$. This fastest rate is called optimal rate of aggregation. Considering a continuous scale of loss functions with various …

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

Deep neural networks achieve optimal classification rates in high dimensions.

Random Fourier features classification achieves fast learning rates with fewer features.

Novel oracle-type inequality for logistic loss in DNNs achieves sharp convergence rates.

New bounds for balanced classification improve understanding of imbalanced datasets.

New learning rules achieve optimal sample complexity for weakly supervised classification.

The paper tackles fast rates in structured prediction problems.

Although kernel methods are widely used in many learning problems, they have poor scalability to large datasets. To address this problem, sketching and stochastic gradient methods are the most commonly used techniques to derive efficient large-scale learning algorithms. In this study, we consider solving a binary class…

Proposes a robust method for counterfactual classification.

The paper uses thermodynamics to improve machine learning representation quality.

k Nearest Neighbor (kNN) method is a simple and popular statistical method for classification and regression. For both classification and regression problems, existing works have shown that, if the distribution of the feature vector has bounded support and the probability density function is bounded away from zero in i…

This paper aims at refined error analysis for binary classification using support vector machine (SVM) with Gaussian kernel and convex loss. Our first result shows that for some loss functions such as the truncated quadratic loss and quadratic loss, SVM with Gaussian kernel can reach the almost optimal learning rate, p…