arXiv Statistics ML
Optimal aggregation in multiclass classification
Read the original on arXiv Statistics ML →The Flow has not summarised this story yet — read it at arXiv Statistics ML.
Related stories
arXiv Machine Learning
Jul 17
Analytical study of the optimal combination of binary classifiers based on classifiers-induced partitioning of the training set
arXiv:2607. 14889v1 Announce Type: new Abstract: This paper studies an optimal linear combination of binary classifiers based on a logical structuration of the dataset via truth tables.
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.
arXiv AI
Jul 7
A Unified Algebraic Framework for Classification Performance Evaluation
arXiv:2607. 04028v1 Announce Type: cross Abstract: We propose a unified algebraic framework for classification performance evaluation that encompasses binary, multiclass, multilabel, ordinal, hierarchical, cost-sensitive, and soft-label settings within a single formalism.
arXiv Machine Learning
Aug 13
Linear-Core Surrogates: Smooth Loss Functions with Linear Rates for Classification and Structured Prediction
arXiv:2604. 27742v2 Announce Type: replace Abstract: A fundamental dichotomy in the theory of classification sets smoothness against statistical efficiency: smooth surrogate losses such as the logistic loss enable fast $O(1/T)$ optimization but yield slow square-root $H$-consistency bounds, while piecewise-linear losses like the Hinge loss achieve optimal linear $H$-consistency rates but are non-differentiable.
arXiv Machine Learning
Oct 16
BOLT: Universal Classifier Training via a Bayes-Error Upper Bound
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.
arXiv Machine Learning
Jun 15
On Rate-Optimal Partitioning Classification from Observable and from Privatised Data
arXiv:2312. 14889v4 Announce Type: replace-cross Abstract: In this paper we revisit the classical method of partitioning classification and prove novel convergence rates under relaxed conditions, both for observable (non-privatised) and for privatised data.