A Neural Tangent Kernel Perspective of Infinite Tree Ensembles

Abstract

In practical situations, the tree ensemble is one of the most popular models along with neural networks. A soft tree is a variant of a decision tree. Instead of using a greedy method for searching splitting rules, the soft tree is trained using a gradient method in which the entire splitting operation is formulated in a differentiable form. Although ensembles of such soft trees have been used increasingly in recent years, little theoretical work has been done to understand their behavior. By considering an ensemble of infinite soft trees, this paper introduces and studies the Tree Neural Tangent Kernel (TNTK), which provides new insights into the behavior of the infinite ensemble of soft trees. Using the TNTK, we theoretically identify several non-trivial properties, such as global convergence of the training, the equivalence of the oblivious tree structure, and the degeneracy of the TNTK induced by the deepening of the trees.

Accepted to ICLR 2022

References in corpus (5)

• Identifying and attacking the saddle point problem in high-dimensional non-convex optimization
• Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer
• Distilling a Neural Network Into a Soft Decision Tree
• Neural Architecture Search on ImageNet in Four GPU Hours: A Theoretically Inspired Perspective
• Learning Accurate Decision Trees with Bandit Feedback via Quantized Gradient Descent