NeurIPS 2016poster31 citations
The Forget-me-not Process
Kieran Milan, Joel Veness, James Kirkpatrick, Michael Bowling, Anna Koop, Demis Hassabis
Abstract
We introduce the Forget-me-not Process, an efficient, non-parametric meta-algorithm for online probabilistic sequence prediction for piecewise stationary, repeating sources. Our method works by taking a Bayesian approach to partition a stream of data into postulated task-specific segments, while simultaneously building a model for each task. We provide regret guarantees with respect to piecewise stationary data sources under the logarithmic loss, and validate the method empirically across a range of sequence prediction and task identification problems.
BibTeX
@inproceedings{NIPS2016_f26dab9b,
author = {Milan, Kieran and Veness, Joel and Kirkpatrick, James and Bowling, Michael and Koop, Anna and Hassabis, Demis},
booktitle = {Advances in Neural Information Processing Systems},
editor = {D. Lee and M. Sugiyama and U. Luxburg and I. Guyon and R. Garnett},
pages = {},
publisher = {Curran Associates, Inc.},
title = {The Forget-me-not Process},
url = {https://proceedings.neurips.cc/paper_files/paper/2016/file/f26dab9bf6a137c3b6782e562794c2f2-Paper.pdf},
volume = {29},
year = {2016}
}