A k-decision tree t (or k-tree) is a recursive partition of a matrix (2D-signal) into k ≥ 1 block matrices (axis-parallel rectangles, leaves) where each rectangle is assigned a real label. Its regression or classification loss to a given matrix D of N entries (labels) is the sum of squared differences over every label in D and its assigned label by t. Given an error parameter ε ∈ (0, 1), a (k, ε)-coreset C of D is a small summarization that provably approximates this loss to every such tree, up to a multiplicative factor of 1 ± ε. In particular, the optimal k-tree of C is a (1 + ε)-approximation to the optimal k-tree of D. We provide the first algorithm that outputs such a (k, ε)-coreset for every such matrix D. The size |C| of the coreset is polynomial in k log(N)/ε, and its construction takes O(Nk) time. This is by forging a link between decision trees from machine learning – to partition trees in computational geometry. Experimental results on sklearn and lightGBM show that applying our coresets on real-world data-sets boosts the computation time of random forests and their parameter tuning by up to x10, while keeping similar accuracy. Full open source code is provided.
|Title of host publication||Advances in Neural Information Processing Systems 34 - 35th Conference on Neural Information Processing Systems, NeurIPS 2021|
|Editors||Marc'Aurelio Ranzato, Alina Beygelzimer, Yann Dauphin, Percy S. Liang, Jenn Wortman Vaughan|
|Publisher||Neural information processing systems foundation|
|Number of pages||13|
|State||Published - 7 Oct 2021|
|Event||35th Conference on Neural Information Processing Systems, NeurIPS 2021 - Virtual, Online|
Duration: 6 Dec 2021 → 14 Dec 2021
|Name||Advances in Neural Information Processing Systems|
|Conference||35th Conference on Neural Information Processing Systems, NeurIPS 2021|
|Period||6/12/21 → 14/12/21|
Bibliographical noteFunding Information:
This research was supported by The ISRAEL SCIENCE FOUNDATION, grant number 379/21.
© 2021 Neural information processing systems foundation. All rights reserved.
ASJC Scopus subject areas
- Computer Networks and Communications
- Information Systems
- Signal Processing