New high-probability generalization bounds are derived via Rademacher complexity for regularized piecewise-linear regression trees, with an efficient GPU-based algorithm and empirical comparisons to piecewise-constant trees.
In: NIPS’15 Proceedings of the 28th International Conference on Neural Information Processing Systems
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2019 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Efficient Regularized Piecewise-Linear Regression Trees
New high-probability generalization bounds are derived via Rademacher complexity for regularized piecewise-linear regression trees, with an efficient GPU-based algorithm and empirical comparisons to piecewise-constant trees.