On Loss Functions and Regret Bounds for Multi-Category Classification

DOI10.1109/TIT.2022.3167635MaRDI QIDQ5096993zbMATH OpenOpenAlexFDO

Authors Zhiqiang Tan, Xinwei Zhang

Publication date 19 August 2022

Published in IEEE Transactions on Information Theory (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/2005.08155

zbMATH Keywords

loss functionsmulti-class settingsregret boundszero-one or cost-weighted classification loss

Mathematics Subject Classification ID

Classification and discrimination; cluster analysis (statistical aspects) (62H30)

Abstract: We develop new approaches in multi-class settings for constructing proper scoring rules and hinge-like losses and establishing corresponding regret bounds with respect to the zero-one or cost-weighted classification loss. Our construction of losses involves deriving new inverse mappings from a concave generalized entropy to a loss through the use of a convex dissimilarity function related to the multi-distribution $f$-divergence. Moreover, we identify new classes of multi-class proper scoring rules, which also recover and reveal interesting relationships between various composite losses currently in use. We establish new classification regret bounds in general for multi-class proper scoring rules by exploiting the Bregman divergences of the associated generalized entropies, and, as applications, provide simple meaningful regret bounds for two specific classes of proper scoring rules. Finally, we derive new hinge-like convex losses, which are tighter convex extensions than related hinge-like losses and geometrically simpler with fewer non-differentiable edges, while achieving similar regret bounds. We also establish a general classification regret bound for all losses which induce the same generalized entropy as the zero-one loss.

Recommendations

• Data-dependent bounds for multi-category classification based on convex losses.
• On the rate of convergence for multi-category classification based on convex losses
• Risk-sensitive loss functions for sparse multi-category classification problems
• Learning Theory
• Multicategory large margin classification methods: hinge losses vs. coherence functions
• Relative loss bounds for multidimensional regression problems
• Surrogate regret bounds for generalized classification performance metrics
• Minimax optimal rates of convergence for multicategory classifications

Cited in

(4)

• scientific article; zbMATH DE number 7626737 (Why is no real title available?)
• scientific article; zbMATH DE number 5251636 (Why is no real title available?)
• Learning Theory
• A Fisher consistent multiclass loss function with variable margin on positive examples

This page was built for publication: On Loss Functions and Regret Bounds for Multi-Category Classification

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5096993)