A Low-Depth Monotone Function that is not an Approximate Junta
Daniel M. Kane

TL;DR
This paper presents a monotone Boolean function with a low-depth decision tree that cannot be closely approximated by small juntas, challenging assumptions about the simplicity of such functions.
Contribution
It introduces a specific example of a low-depth monotone function that defies approximation by small juntas, highlighting limitations in existing approximation techniques.
Findings
Low-depth monotone functions can be complex and not approximable by small juntas.
The example challenges previous beliefs about the simplicity of low-depth monotone functions.
Implications for the analysis of Boolean functions and complexity theory.
Abstract
We provide an example of a monotone Boolean function on the hypercube given by a low depth decision tree that is not well approximated by any k-junta for small k.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsMachine Learning and Algorithms · Machine Learning and Data Classification · Rough Sets and Fuzzy Logic
