Superpolynomial Lower Bounds for Learning Monotone Classes

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Koch, Strassle, and Tan [SODA 2023], show that, under the randomized exponential time hypothesis, there is no distribution-free PAC-learning algorithm that runs in time nÕ(log log s) for the classes of n-variable size-s DNF, size-s Decision Tree, and log s-Junta by DNF (that returns a DNF hypothesis). Assuming a natural conjecture on the hardness of set cover, they give the lower bound nΩ(log s). This matches the best known upper bound for n-variable size-s Decision Tree, and log s-Junta. In this paper, we give the same lower bounds for PAC-learning of n-variable size-s Monotone DNF, size-s Monotone Decision Tree, and Monotone log s-Junta by DNF. This solves the open problem proposed by Koch, Strassle, and Tan and subsumes the above results. The lower bound holds, even if the learner knows the distribution, can draw a sample according to the distribution in polynomial time, and can compute the target function on all the points of the support of the distribution in polynomial time.

Original languageEnglish
Title of host publicationApproximation, Randomization, and Combinatorial Optimization. Algorithms and Techniques, APPROX/RANDOM 2023
EditorsNicole Megow, Adam Smith
ISBN (Electronic)9783959772969
DOIs
StatePublished - Sep 2023
Event26th International Conference on Approximation Algorithms for Combinatorial Optimization Problems, APPROX 2023 and the 27th International Conference on Randomization and Computation, RANDOM 2023 - Atlanta, United States
Duration: 11 Sep 202313 Sep 2023

Publication series

NameLeibniz International Proceedings in Informatics, LIPIcs
Volume275

Conference

Conference26th International Conference on Approximation Algorithms for Combinatorial Optimization Problems, APPROX 2023 and the 27th International Conference on Randomization and Computation, RANDOM 2023
Country/TerritoryUnited States
CityAtlanta
Period11/09/2313/09/23

Keywords

  • Lower Bound
  • Monotone DNF
  • Monotone Decision Tree
  • Monotone Junta
  • PAC Learning

All Science Journal Classification (ASJC) codes

  • Software

Fingerprint

Dive into the research topics of 'Superpolynomial Lower Bounds for Learning Monotone Classes'. Together they form a unique fingerprint.

Cite this