Timezone: »

 
Spotlight
Regression-tree Tuning in a Streaming Setting
Samory Kpotufe · Francesco Orabona

Sat Dec 07 11:52 AM -- 11:56 AM (PST) @ Harvey's Convention Center Floor, CC
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 $\tilde{O}(n^{-2/(2+d)})$ 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.

Author Information

Samory Kpotufe (Princeton University)
Francesco Orabona (Boston University)

More from the Same Authors