English

Online Learning Without Prior Information

Machine Learning 2017-06-07 v2 Machine Learning

Abstract

The vast majority of optimization and online learning algorithms today require some prior information about the data (often in the form of bounds on gradients or on the optimal parameter value). When this information is not available, these algorithms require laborious manual tuning of various hyperparameters, motivating the search for algorithms that can adapt to the data with no prior information. We describe a frontier of new lower bounds on the performance of such algorithms, reflecting a tradeoff between a term that depends on the optimal parameter value and a term that depends on the gradients' rate of growth. Further, we construct a family of algorithms whose performance matches any desired point on this frontier, which no previous algorithm reaches.

Keywords

Cite

@article{arxiv.1703.02629,
  title  = {Online Learning Without Prior Information},
  author = {Ashok Cutkosky and Kwabena Boahen},
  journal= {arXiv preprint arXiv:1703.02629},
  year   = {2017}
}

Comments

12 pages main text; 35 pages total; COLT 2017

R2 v1 2026-06-22T18:39:09.451Z