English
Related papers

Related papers: Classification Error Bound for Low Bayes Error Con…

200 papers

In critical decision support systems based on medical imaging, the reliability of AI-assisted decision-making is as relevant as predictive accuracy. Although deep learning models have demonstrated significant accuracy, they frequently…

Computer Vision and Pattern Recognition · Computer Science 2026-02-13 Hua Xu , Julián D. Arias-Londoño , Juan I. Godino-Llorente

Probabilistic classifiers output confidence scores along with their predictions, and these confidence scores should be calibrated, i.e., they should reflect the reliability of the prediction. Confidence scores that minimize standard metrics…

We study the performance -- and specifically the rate at which the error probability converges to zero -- of Machine Learning (ML) classification techniques. Leveraging the theory of large deviations, we provide the mathematical conditions…

Machine Learning · Statistics 2023-01-18 Paolo Braca , Leonardo M. Millefiori , Augusto Aubry , Stefano Marano , Antonio De Maio , Peter Willett

We make two contributions to the problem of estimating the $L_1$ calibration error of a binary classifier from a finite dataset. First, we provide an upper bound for any classifier where the calibration function has bounded variation.…

In machine learning, the selection of a promising model from a potentially large number of competing models and the assessment of its generalization performance are critical tasks that need careful consideration. Typically, model selection…

Machine Learning · Statistics 2023-02-06 Pascal Rink , Werner Brannath

Large language models (LLMs) have shown remarkable adaptability to diverse tasks, by leveraging context prompts containing instructions, or minimal input-output examples. However, recent work revealed they also exhibit label bias -- an…

Computation and Language · Computer Science 2024-05-07 Yuval Reif , Roy Schwartz

In many applications in biology, engineering and economics, identifying similarities and differences between distributions of data from complex processes requires comparing finite categorical samples of discrete counts. Statistical…

Methodology · Statistics 2023-07-11 Francesco Camaglia , Ilya Nemenman , Thierry Mora , Aleksandra M. Walczak

Machine learning (ML) methods are highly flexible, but their ability to approximate the true data-generating process is fundamentally constrained by finite samples. We characterize a universal lower bound, the Limits-to-Learning Gap (LLG),…

Machine Learning · Statistics 2025-12-16 Zhimin Chen , Bryan Kelly , Semyon Malamud

A well-known technique in estimating probabilities of rare events in general and in information theory in particular (used, e.g., in the sphere-packing bound), is that of finding a reference probability measure under which the event of…

Information Theory · Computer Science 2014-12-23 Rami Atar , Neri Merhav

We construct a classifier which attains the rate of convergence $\log n/n$ under sparsity and margin assumptions. An approach close to the one met in approximation theory for the estimation of function is used to obtain this result. The…

Statistics Theory · Mathematics 2016-08-16 Guillaume Lecué

Recent advances in probabilistic deep learning enable efficient amortized Bayesian inference in settings where the likelihood function is only implicitly defined by a simulation program (simulation-based inference; SBI). But how faithful is…

Machine Learning · Computer Science 2024-06-07 Marvin Schmitt , Paul-Christian Bürkner , Ullrich Köthe , Stefan T. Radev

A loss function measures the discrepancy between the true values and their estimated fits, for a given instance of data. In classification problems, a loss function is said to be proper if a minimizer of the expected loss is the true…

Information Theory · Computer Science 2020-01-03 Amichai Painsky , Gregory W. Wornell

This paper presents novel experiments shedding light on the shortcomings of current metrics for assessing biases of gender discrimination made by machine learning algorithms on textual data. We focus on the Bios dataset, and our learning…

Computation and Language · Computer Science 2023-06-09 Fanny Jourdan , Laurent Risser , Jean-Michel Loubes , Nicholas Asher

Mislabeled data is a pervasive issue that undermines the performance of machine learning systems in real-world applications. An effective approach to mitigate this problem is to detect mislabeled instances and subject them to special…

Machine Learning · Computer Science 2025-11-05 Ilies Chibane , Thomas George , Pierre Nodet , Vincent Lemaire

In many parameter estimation problems, the exact model is unknown and is assumed to belong to a set of candidate models. In such cases, a predetermined data-based selection rule selects a parametric model from a set of candidates before the…

Signal Processing · Electrical Eng. & Systems 2025-04-25 Nadav Harel , Tirza Routtenberg

The paper presents a comparative study of the performance of Back Propagation and Instance Based Learning Algorithm for classification tasks. The study is carried out by a series of experiments will all possible combinations of parameter…

Machine Learning · Computer Science 2016-04-20 Nadia Kanwal , Erkan Bostanci

We study ``selective'' or ``conditional'' classification problems under an agnostic setting. Classification tasks commonly focus on modeling the relationship between features and categories that captures the vast majority of data. In…

Machine Learning · Computer Science 2025-02-04 Jizhou Huang , Brendan Juba

A lower bound is an important tool for predicting the performance that an estimator can achieve under a particular statistical model. Bayesian bounds are a kind of such bounds which not only utilizes the observation statistics but also…

Statistics Theory · Mathematics 2023-03-02 Shuo Tang , Gerald LaMountain , Tales Imbiriba , Pau Closas

With model trustworthiness being crucial for sensitive real-world applications, practitioners are putting more and more focus on improving the uncertainty calibration of deep neural networks. Calibration errors are designed to quantify the…

Machine Learning · Computer Science 2024-03-14 Sebastian G. Gruber , Florian Buettner

We present an information-theoretic framework for bounding the number of labeled samples needed to train a classifier in a parametric Bayesian setting. We derive bounds on the average $L_p$ distance between the learned classifier and the…

Information Theory · Computer Science 2017-11-20 Matthew Nokleby , Ahmad Beirami , Robert Calderbank