Multiclass classification with bandit feedback using adaptive regularization
From MaRDI portal
Publication:1945036
DOI10.1007/s10994-012-5321-8zbMath1260.68324MaRDI QIDQ1945036
Publication date: 28 March 2013
Published in: Machine Learning (Search for Journal in Brave)
Full work available at URL: https://doi.org/10.1007/s10994-012-5321-8
68T05: Learning and adaptive systems in artificial intelligence
68W27: Online algorithms; streaming algorithms
Related Items
Sharp bounds on the price of bandit feedback for several models of mistake-bounded online learning, New bounds on the price of bandit feedback for mistake-bounded online multiclass learning
Uses Software
Cites Work
- 10.1162/jmlr.2003.3.4-5.951
- 10.1162/153244303321897663
- Bandit problems with side observations
- A Second-Order Perceptron Algorithm
- Ridge Regression: Biased Estimation for Nonorthogonal Problems
- Relative loss bounds for on-line density estimation with the exponential family of distributions
- On the learnability and design of output codes for multiclass problems