### Abstract

We consider the problem of maintaining the data-structures of a partition-based regression procedure in a setting where the training data arrives sequentially over time. We prove that it is possible to maintain such a structure in time O(log n) at any time step n while achieving a nearly-optimal regression rate of Õ (n^{-2}/(2+d)) in terms of the unknown metric dimension d. Finally we prove a new regression lower-bound which is independent of a given data size, and hence is more appropriate for the streaming setting.

Original language | English (US) |
---|---|

Journal | Advances in Neural Information Processing Systems |

State | Published - Jan 1 2013 |

Event | 27th Annual Conference on Neural Information Processing Systems, NIPS 2013 - Lake Tahoe, NV, United States Duration: Dec 5 2013 → Dec 10 2013 |

### All Science Journal Classification (ASJC) codes

- Computer Networks and Communications
- Information Systems
- Signal Processing

## Fingerprint Dive into the research topics of 'Regression-tree tuning in a streaming setting'. Together they form a unique fingerprint.

## Cite this

Kpotufe, S., & Orabona, F. (2013). Regression-tree tuning in a streaming setting.

*Advances in Neural Information Processing Systems*.