Multiclass learnability and the ERM principle

MaRDI QIDQ5744842zbMATH OpenFDO

Authors Amit Daniely, Sivan Sabato, Shai Ben-David, Shai Shalev-Shwartz

Publication date 19 February 2016

Full work available at URL https://arxiv.org/abs/1308.2893, http://jmlr.csail.mit.edu/papers/v16/daniely15a.html

zbMATH Keywords

ERMmulticlasssample complexity

Mathematics Subject Classification ID

Classification and discrimination; cluster analysis (statistical aspects) (62H30) Learning and adaptive systems in artificial intelligence (68T05)

Recommendations

• ERM learning algorithm for multi-class classification
• New bounds on the price of bandit feedback for mistake-bounded online multiclass learning
• New bounds on the price of bandit feedback for mistake-bounded online multiclass learning
• Risk bounds for statistical learning

Cited in

(13)

• New bounds on the price of bandit feedback for mistake-bounded online multiclass learning
• Unconfused ultraconservative multiclass algorithms
• ERM learning algorithm for multi-class classification
• Learning Multi-class Theories in ILP
• Erratum: Constructing Multiclass Learners from Binary Learners: A Simple Black-Box Analysis of the Generalization Errors
• Inapproximability of truthful mechanisms via generalizations of the Vapnik-Chervonenkis dimension
• New bounds on the price of bandit feedback for mistake-bounded online multiclass learning
• Algorithmic Learning Theory
• On the learnability and design of output codes for multiclass problems
• A characterization of list learnability
• Realizable learning is all you need
• Multiclass learnability does not imply sample compression
• Model Selection for Multivalued-Treatment Policy Learning in Observational Studies

This page was built for publication: Multiclass learnability and the ERM principle

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5744842)