Online Bounds for Bayesian Algorithms

@inproceedings{Kakade2004OnlineBF,
  title={Online Bounds for Bayesian Algorithms},
  author={Sham M. Kakade and Andrew Y. Ng},
  booktitle={NIPS},
  year={2004}
}
We present a competitive analysis of Bayesian learning algorithms in the online learning setting and show that many simple Bayesian algorithms (such as Gaussian linear regression and Bayesian logistic regression) perform favorably when compared, in retrospect, to the single best model in the model class. The analysis does not assume that the Bayesian algorithms’ modeling assumptions are “correct,” and our bounds hold even if the data is adversarially chosen. For Gaussian linear regression… CONTINUE READING

Similar Papers

Loading similar papers…