DNF Learning via Locally Mixing Random Walks

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Alman, Josh, Nadimpalli, Shivam, Patel, Shyamal, Servedio, Rocco A.
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908378774634496
author Alman, Josh
Nadimpalli, Shivam
Patel, Shyamal
Servedio, Rocco A.
author_facet Alman, Josh
Nadimpalli, Shivam
Patel, Shyamal
Servedio, Rocco A.
contents We give two results on PAC learning DNF formulas using membership queries in the challenging "distribution-free" learning framework, where learning algorithms must succeed for an arbitrary and unknown distribution over $\{0,1\}^n$. (1) We first give a quasi-polynomial time "list-decoding" algorithm for learning a single term of an unknown DNF formula. More precisely, for any target $s$-term DNF formula $f = T_1 \vee \cdots \vee T_s$ over $\{0,1\}^n$ and any unknown distribution $D$ over $\{0,1\}^n$, our algorithm, which uses membership queries and random examples from $D$, runs in $\textsf{quasipoly}(n,s)$ time and outputs a list $L$ of candidate terms such that with high probability some term $T_i$ of $f$ belongs to $L$. (2) We then use result (1) to give a $\textsf{quasipoly}(n,s)$-time algorithm, in the distribution-free PAC learning model with membership queries, for learning the class of size-$s$ DNFs in which all terms have the same size. Our algorithm learns using a DNF hypothesis. The key tool used to establish result (1) is a new result on "locally mixing random walks," which, roughly speaking, shows that a random walk on a graph that is covered by a small number of expanders has a non-negligible probability of mixing quickly in a subset of these expanders.
format Preprint
id arxiv_https___arxiv_org_abs_2505_18839
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle DNF Learning via Locally Mixing Random Walks
Alman, Josh
Nadimpalli, Shivam
Patel, Shyamal
Servedio, Rocco A.
Data Structures and Algorithms
We give two results on PAC learning DNF formulas using membership queries in the challenging "distribution-free" learning framework, where learning algorithms must succeed for an arbitrary and unknown distribution over $\{0,1\}^n$. (1) We first give a quasi-polynomial time "list-decoding" algorithm for learning a single term of an unknown DNF formula. More precisely, for any target $s$-term DNF formula $f = T_1 \vee \cdots \vee T_s$ over $\{0,1\}^n$ and any unknown distribution $D$ over $\{0,1\}^n$, our algorithm, which uses membership queries and random examples from $D$, runs in $\textsf{quasipoly}(n,s)$ time and outputs a list $L$ of candidate terms such that with high probability some term $T_i$ of $f$ belongs to $L$. (2) We then use result (1) to give a $\textsf{quasipoly}(n,s)$-time algorithm, in the distribution-free PAC learning model with membership queries, for learning the class of size-$s$ DNFs in which all terms have the same size. Our algorithm learns using a DNF hypothesis. The key tool used to establish result (1) is a new result on "locally mixing random walks," which, roughly speaking, shows that a random walk on a graph that is covered by a small number of expanders has a non-negligible probability of mixing quickly in a subset of these expanders.
title DNF Learning via Locally Mixing Random Walks
topic Data Structures and Algorithms
url https://arxiv.org/abs/2505.18839