Volumetric spanners: an efficient exploration basis for learning

MaRDI QIDQ3188058zbMATH OpenFDO

Authors Elad Hazan, Zohar S. Karnin

Publication date 16 August 2016

Full work available at URL http://jmlr.csail.mit.edu/papers/v17/hazan16a.html

zbMATH Keywords

barycentric spannerhard margin linear regressionlinear banditsvolumetric spanner

Mathematics Subject Classification ID

Linear regression; mixed models (62J05) Learning and adaptive systems in artificial intelligence (68T05)

Recommendations

• Exploration-exploitation tradeoff using variance estimates in multi-armed bandits
• Sparsity, variance and curvature in multi-armed bandits
• 10.1162/153244303321897663
• Better algorithms for benign bandits
• Optimal learning and experimentation in bandit problems.

Cited in

(3)

• Efficient online linear optimization with approximation algorithms
• A unified analysis of nonstochastic delayed feedback for combinatorial semi-bandits, linear bandits, and MDPs
• Bayesian design principles for frequentist sequential learning

This page was built for publication: Volumetric spanners: an efficient exploration basis for learning

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q3188058)