On the equivalence of Occam algorithms

08/11/2023
by   Zaman Keinath-Esmail, et al.
0

Blumer et al. (1987, 1989) showed that any concept class that is learnable by Occam algorithms is PAC learnable. Board and Pitt (1990) showed a partial converse of this theorem: for concept classes that are closed under exception lists, any class that is PAC learnable is learnable by an Occam algorithm. However, their Occam algorithm outputs a hypothesis whose complexity is δ-dependent, which is an important limitation. In this paper, we show that their partial converse applies to Occam algorithms with δ-independent complexities as well. Thus, we provide a posteriori justification of various theoretical results and algorithm design methods which use the partial converse as a basis for their work.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
03/30/2023

Online Learning and Disambiguations of Partial Concept Classes

In a recent article, Alon, Hanneke, Holzman, and Moran (FOCS '21) introd...
research
02/12/2019

VC Classes are Adversarially Robustly Learnable, but Only Improperly

We study the question of learning an adversarially robust predictor. We ...
research
08/22/2022

On the non-efficient PAC learnability of acyclic conjunctive queries

This note serves three purposes: (i) we provide a self-contained exposit...
research
09/19/2013

Predictive PAC Learning and Process Decompositions

We informally call a stochastic process learnable if it admits a general...
research
02/10/2022

On characterizations of learnability with computable learners

We study computable PAC (CPAC) learning as introduced by Agarwal et al. ...
research
11/25/2020

Learnability and Positive Equivalence Relations

Prior work of Gavryushkin, Khoussainov, Jain and Stephan investigated wh...
research
02/06/2023

Find a witness or shatter: the landscape of computable PAC learning

This paper contributes to the study of CPAC learnability – a computable ...

Please sign up or login with your details

Forgot password? Click here to reset