Bandit Multiclass Linear Classification: Efficient Algorithms for the Separable Case

Balázs Szörényi
Balázs Szörényi
Devanathan Thiruvenkatachari
Devanathan Thiruvenkatachari

International Conference on Machine Learning, pp. 624-633, 2019.

Cited by: 2|Views48
EI

Abstract:

We study the problem of efficient online multiclass linear classification with bandit feedback, where all examples belong to one of $K$ classes and lie in the $d$-dimensional Euclidean space. Previous works have left open the challenge of designing efficient algorithms with finite mistake bounds when the data is linearly separable by a ma...More

Code:

Data:

Your rating :
0

 

Tags
Comments