Differentially- and non-differentially-private random decision trees

  title={Differentially- and non-differentially-private random decision trees},
  author={Mariusz Bojarski and Anna Choromanska and Krzysztof Choromanski and Yann LeCun},
We consider supervised learning with random decision trees, where the tree construction is completely random. The method was used as a heuristic working well in practice despite the simplicity of the setting, but with almost no theoretical guarantees. The goal of this paper is to shed new light on the entire paradigm. We provide strong theoretical guarantees regarding learning with random decision trees. We present and compare three different variants of the algorithm that have minimal memory… CONTINUE READING
Recent Discussions
This paper has been referenced on Twitter 2 times over the past 90 days. VIEW TWEETS
12 Extracted Citations
16 Extracted References
Similar Papers

Similar Papers

Loading similar papers…