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: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: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: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.
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: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.
arXiv:2607.22258v2 Announce Type: replace Abstract: Models trained on long-tailed data using standard softmax tend to exhibit higher training error and a larger generalisation gap for classes with fe...
The paper analyzes training dynamics of multiclass logistic regression on high‑dimensional Gaussian mixture models with many classes. It finds that learning proceeds sequentially from the most to the least frequent classes and, when class priors follow a power‑law, the cross‑entropy risk evolves through an initial plateau, a power‑law decay phase, and a final convergence phase. The study also shows how model capacity and optimization trade‑off under a fixed compute budget, leading to a compute‑optimal scaling law that prescribes model size and training time as functions of compute.
arXiv:2609.06873v1 Announce Type: cross Abstract: We study how a limited labeling budget should be allocated to minimize multiclass zero-one classification risk. We consider parametric classification...
The paper investigates the consistency of surrogate loss methods for classification and policy learning when the set of admissible classifiers is constrained, such as by interpretability or fairness requirements. It shows that hinge loss is the only surrogate that preserves consistency when constraints limit only the prediction set, but consistency can fail if constraints also restrict the functional form. The authors derive conditions guaranteeing consistency for hinge-risk-minimizing classifiers and use these results to design efficient hinge-loss-based procedures for monotone classification problems.
arXiv:2608.30561v1 Announce Type: cross Abstract: Informative label missingness can change the usual efficiency ordering between completely and partially labelled classifiers because the pattern of m...
The paper investigates binary classification with abstention under separate class‑conditional error constraints, aiming to minimize abstention while keeping both error types below specified thresholds. It derives the distribution‑free minimax rate of excess abstention risk, introduces surrogate‑loss formulations for computational feasibility with models like neural networks, and provides finite‑sample guarantees for excess surrogate ambiguity risk. The authors also formulate the learning task as a constrained optimization problem, analyze its computational complexity in the convex setting, and empirically evaluate the approach against a competing method on several datasets.