Efficient Transductive Online Learning via Randomized Rounding

@inproceedings{CesaBianchi2011EfficientTO,
  title={Efficient Transductive Online Learning via Randomized Rounding},
  author={Nicol{\`o} Cesa-Bianchi and Ohad Shamir},
  booktitle={Empirical Inference},
  year={2011}
}
Most online algorithms used in machine learning today are based on variants of mirror descent or follow-the-leader. In this paper, we present an online algorithm based on a completely different approach, which combines “random playout” and randomized rounding of loss subgradients. As an application of our approach, we provide the first computationally efficient online algorithm for collaborative filtering with trace-norm constrained matrices. As a second application, we solve an open question… CONTINUE READING

From This Paper

Topics from this paper.

Similar Papers

Loading similar papers…