Adaptive Exact Learning of Decision Trees from Membership Queries

Nader H. Bshouty; Catherine A. Haddad-Zaknoon

Adaptive Exact Learning of Decision Trees from Membership Queries

Nader H. Bshouty, Catherine A. Haddad-Zaknoon

Computer Science

Technion - Israel Institute of Technology

Research output: Contribution to journal › Conference article › peer-review

Abstract

In this paper we study the adaptive learnability of decision trees of depth at most d from membership queries. This has many applications in automated scientific discovery such as drugs development and software update problem. Feldman solves the problem in a randomized polynomial time algorithm that asks Õ(2^2d) log n queries. Kushilevitz-Mansour solve it in a deterministic polynomial time algorithm that asks 2¹⁸d+o(d⁾ log n queries. We improve the query complexity of both algorithms. We give a randomized polynomial time algorithm that asks Õ(2^2d) + 2^d log n queries and a deterministic polynomial time algorithm that asks 2^5.83d + 2²d+o(d⁾ log n queries.

Original language	English
Pages (from-to)	207-234
Number of pages	28
Journal	Proceedings of Machine Learning Research
Volume	98
State	Published - 2019
Event	30th International Conference on Algorithmic Learning Theory, ALT 2019 - Chicago, United States Duration: 22 Mar 2019 → 24 Mar 2019 https://proceedings.mlr.press/v98

Keywords

Adaptive Learning
Decision Trees
Exact Learning
Membership Queries

All Science Journal Classification (ASJC) codes

Artificial Intelligence
Software
Control and Systems Engineering
Statistics and Probability

Cite this

@article{aa652f8af83c40d1ac185a027dfeee1e,

title = "Adaptive Exact Learning of Decision Trees from Membership Queries",

abstract = "In this paper we study the adaptive learnability of decision trees of depth at most d from membership queries. This has many applications in automated scientific discovery such as drugs development and software update problem. Feldman solves the problem in a randomized polynomial time algorithm that asks {\~O}(22d) log n queries. Kushilevitz-Mansour solve it in a deterministic polynomial time algorithm that asks 218d+o(d) log n queries. We improve the query complexity of both algorithms. We give a randomized polynomial time algorithm that asks {\~O}(22d) + 2d log n queries and a deterministic polynomial time algorithm that asks 25.83d + 22d+o(d) log n queries.",

keywords = "Adaptive Learning, Decision Trees, Exact Learning, Membership Queries",

author = "Bshouty, \{Nader H.\} and Haddad-Zaknoon, \{Catherine A.\}",

note = "Publisher Copyright: {\textcopyright} 2019 Proceedings of Machine Learning Research. All rights reserved.; 30th International Conference on Algorithmic Learning Theory, ALT 2019 ; Conference date: 22-03-2019 Through 24-03-2019",

year = "2019",

language = "الإنجليزيّة",

volume = "98",

pages = "207--234",

journal = "Proceedings of Machine Learning Research",

issn = "2640-3498",

publisher = "ML Research Press",

url = "https://proceedings.mlr.press/v98",

}

TY - JOUR

T1 - Adaptive Exact Learning of Decision Trees from Membership Queries

AU - Bshouty, Nader H.

AU - Haddad-Zaknoon, Catherine A.

PY - 2019

Y1 - 2019

N2 - In this paper we study the adaptive learnability of decision trees of depth at most d from membership queries. This has many applications in automated scientific discovery such as drugs development and software update problem. Feldman solves the problem in a randomized polynomial time algorithm that asks Õ(22d) log n queries. Kushilevitz-Mansour solve it in a deterministic polynomial time algorithm that asks 218d+o(d) log n queries. We improve the query complexity of both algorithms. We give a randomized polynomial time algorithm that asks Õ(22d) + 2d log n queries and a deterministic polynomial time algorithm that asks 25.83d + 22d+o(d) log n queries.

AB - In this paper we study the adaptive learnability of decision trees of depth at most d from membership queries. This has many applications in automated scientific discovery such as drugs development and software update problem. Feldman solves the problem in a randomized polynomial time algorithm that asks Õ(22d) log n queries. Kushilevitz-Mansour solve it in a deterministic polynomial time algorithm that asks 218d+o(d) log n queries. We improve the query complexity of both algorithms. We give a randomized polynomial time algorithm that asks Õ(22d) + 2d log n queries and a deterministic polynomial time algorithm that asks 25.83d + 22d+o(d) log n queries.

KW - Adaptive Learning

KW - Decision Trees

KW - Exact Learning

KW - Membership Queries

UR - http://www.scopus.com/inward/record.url?scp=85113691737&partnerID=8YFLogxK

M3 - مقالة من مؤنمر

SN - 2640-3498

VL - 98

SP - 207

EP - 234

JO - Proceedings of Machine Learning Research

JF - Proceedings of Machine Learning Research

T2 - 30th International Conference on Algorithmic Learning Theory, ALT 2019

Y2 - 22 March 2019 through 24 March 2019

ER -

Adaptive Exact Learning of Decision Trees from Membership Queries

Abstract

Keywords

All Science Journal Classification (ASJC) codes

Other files and links

Fingerprint

Cite this