Learning Binary Decision Trees by Argmin Differentiation - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2021

Learning Binary Decision Trees by Argmin Differentiation

Abstract

We address the problem of learning binary decision trees that partition data for some downstream task. We propose to learn discrete parameters (i.e., for tree traversals and node pruning) and continuous parameters (i.e., for tree split functions and prediction functions) simultaneously using argmin differentiation. We do so by sparsely relaxing a mixed-integer program for the discrete parameters, to allow gradients to pass through the program to continuous parameters. We derive customized algorithms to efficiently compute the forward and backward passes. This means that our tree learning procedure can be used as an (implicit) layer in arbitrary deep networks, and can be optimized with arbitrary loss functions. We demonstrate that our approach produces binary trees that are competitive with existing single tree and ensemble approaches, in both supervised and unsupervised settings. Further, apart from greedy approaches (which do not have competitive accuracies), our method is faster to train than all other tree-learning baselines we compare with. The code for reproducing the results is available at https://github.com/vzantedeschi/LatentTrees.
Fichier principal
Vignette du fichier
2010.04627.pdf (1.21 Mo) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-03399069 , version 1 (23-10-2021)

Identifiers

  • HAL Id : hal-03399069 , version 1

Cite

Valentina Zantedeschi, Matt J Kusner, Vlad Niculae. Learning Binary Decision Trees by Argmin Differentiation. International Conference on Machine Learning, Jun 2021, Virtual, United Kingdom. ⟨hal-03399069⟩
38 View
119 Download

Share

Gmail Facebook X LinkedIn More