arXiv Machine Learning October 16, 2026 By Mohammadreza Tavasoli Naeini, Ali Bereyhi, Morteza Noshad, Ben Liang, Alfred O. Hero III

BOLT: Universal Classifier Training via a Bayes-Error Upper Bound

Read the original on arXiv Machine Learning →

The paper presents BOLT, a new loss function that uses a universal upper bound on the Bayes error rate (BER) derived from classifier-output samples. This bound is tight for binary classification and the authors analyze the max‑sum gap in multiclass settings. Experiments on synthetic and real datasets demonstrate that BOLT training can achieve lower held‑out classification error than traditional cross‑entropy training.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

arXiv Statistics ML

Oct 21

Optimal aggregation in multiclass classification

arXiv:2610.28025v1 Announce Type: cross Abstract: This paper studies the problem of aggregation in multiclass classification, generalizing existing results for binary classification. Given a finite d...

By Felix Abramovich, Or Davidovitch-Servadio

arXiv Machine Learning

Jun 17

Does the Data Processing Inequality Reflect Practice? On the Utility of Low-Level Tasks

arXiv:2512. 21315v2 Announce Type: replace Abstract: The data processing inequality is an information-theoretic principle stating that the information content of a signal cannot be increased by processing the observations.

By Roy Turgeman, Tom Tirer

benchmarks

arXiv Machine Learning

Jun 16

Imbalanced Classification under Capacity Constraints

arXiv:2605. 03289v2 Announce Type: replace-cross Abstract: Detecting observations from a minority class under severe class imbalance is a central challenge in applications such as fraud detection, medical screening, and industrial quality control.

By Daniel Fraiman, Ricardo Fraiman

arXiv Machine Learning

Oct 21

Using Set Learning to Improve Set-Valued Classifiers on Long-tailed Data

arXiv:2610.27443v1 Announce Type: new Abstract: Set-valued classification (SVC) offers a practical approach to communicating uncertainty while maintaining accuracy by predicting variable-sized sets p...

By Kevin Kasa, Scott C. Lowe, Graham W. Taylor

arXiv Machine Learning

Aug 11

Efficient and Noise-Tolerant PAC Learning of Multiclass Linear Classifiers

arXiv:2605. 18662v2 Announce Type: replace Abstract: Noise-tolerant PAC learning of linear models has been of central interests in machine learning community since the last century.

By Rita Adhikari, Shiwei Zeng

efficiency

arXiv Machine Learning

Jul 27

Class-Balanced Softmax: A Bayes Theory-Based Method for Long-Tailed Recognition

arXiv:2607. 22258v1 Announce Type: new Abstract: Deep learning models using traditional softmax classifiers have achieved remarkable success in various classification tasks.

By Yi-Hang Zhu, Rajeev Raman, Shiqi Su, Jianyuan Sun, Xinyu Yang, Nan Xing, Huiyu Zhou

benchmarks

One email a morning, machine-written

Related stories

Optimal aggregation in multiclass classification

Does the Data Processing Inequality Reflect Practice? On the Utility of Low-Level Tasks

Imbalanced Classification under Capacity Constraints

Using Set Learning to Improve Set-Valued Classifiers on Long-tailed Data

Efficient and Noise-Tolerant PAC Learning of Multiclass Linear Classifiers

Class-Balanced Softmax: A Bayes Theory-Based Method for Long-Tailed Recognition