Random Hinge Forest for Differentiable Learning
This work addresses the challenge of making decision forests compatible with gradient-based optimization for machine learning practitioners, though it appears incremental as it builds on existing forest methods.
The authors tackled the problem of integrating decision forests into differentiable computation graphs for end-to-end optimization, proposing random hinge forests as a simple and efficient variant that demonstrated performance across various UCI and image datasets like MNIST, Letter, and USPS.
We propose random hinge forests, a simple, efficient, and novel variant of decision forests. Importantly, random hinge forests can be readily incorporated as a general component within arbitrary computation graphs that are optimized end-to-end with stochastic gradient descent or variants thereof. We derive random hinge forest and ferns, focusing on their sparse and efficient nature, their min-max margin property, strategies to initialize them for arbitrary network architectures, and the class of optimizers most suitable for optimizing random hinge forest. The performance and versatility of random hinge forests are demonstrated by experiments incorporating a variety of of small and large UCI machine learning data sets and also ones involving the MNIST, Letter, and USPS image datasets. We compare random hinge forests with random forests and the more recent backpropagating deep neural decision forests.