MLLGMar 20, 2020

Probabilistic learning of boolean functions applied to the binary classification problem with categorical covariates

arXiv:2003.09454v1
Originality Synthesis-oriented
AI Analysis

This work addresses binary classification problems for domains with categorical data, but it appears incremental as it builds on existing boolean function methods without claiming major breakthroughs.

The authors tackled binary classification with categorical covariates by modeling it as estimating a partition on Bernoulli data using boolean functions, and they proposed two algorithms for learning these functions from binary data.

In this work we cast the problem of binary classification in terms of estimating a partition on Bernoulli data. When the explanatory variables are all categorical, the problem can be modelled using the language of boolean functions. We offer a probabilistic analysis of the problem, and propose two algorithms for learning boolean functions from binary data.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes