# Convolutional Model Trees

arXiv: https://arxiv.org/abs/2511.12725 · HTML: https://mlsanity.com/paper/2511.12725/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 3 of its 10 references that are in the map.
- First posted on arXiv 16 Nov 2025.

## Builds on (most cited first, 3 of 3)

- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [Distilling a Neural Network Into a Soft Decision Tree](https://mlsanity.com/paper/1711.09784/) (2017)
- [Fast Linear Model Trees by PILOT](https://mlsanity.com/paper/2302.03931/) (2023)

## Built on by (most cited first, 1 of 1)

- [Rotation-Robust Regression with Convolutional Model Trees](https://mlsanity.com/paper/2601.04899/) (2026)

## Abstract (arXiv)

A method for creating a forest of model trees to fit samples of a function defined on images is described in several steps: down-sampling the images, determining a tree's hyperplanes, applying convolutions to the hyperplanes to handle small distortions of training images, and creating forests of model trees to increase accuracy and achieve a smooth fit. A 1-to-1 correspondence among pixels of images, coefficients of hyperplanes and coefficients of leaf functions offers the possibility of dealing with larger distortions such as arbitrary rotations or changes of perspective. A theoretical method for smoothing forest outputs to produce a continuously differentiable approximation is described. Within that framework, a training procedure is proved to converge.