Regression-tree tuning in a streaming setting

Samory Kpotufe, Francesco Orabona

Research output: Chapter in Book/Report/Conference proceedingConference contribution

6 Scopus citations


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 languageEnglish (US)
Title of host publicationAdvances in Neural Information Processing Systems
PublisherNeural information processing systems foundation
StatePublished - Jan 1 2013
Externally publishedYes


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

Cite this