Online Learning and Disambiguations of Partial Concept Classes

03/30/2023
by   Tsun-Ming Cheung, et al.
0

In a recent article, Alon, Hanneke, Holzman, and Moran (FOCS '21) introduced a unifying framework to study the learnability of classes of partial concepts. One of the central questions studied in their work is whether the learnability of a partial concept class is always inherited from the learnability of some “extension” of it to a total concept class. They showed this is not the case for PAC learning but left the problem open for the stronger notion of online learnability. We resolve this problem by constructing a class of partial concepts that is online learnable, but no extension of it to a class of total concepts is online learnable (or even PAC learnable).

READ FULL TEXT

page 1

page 2

page 3

page 4

research
08/11/2023

On the equivalence of Occam algorithms

Blumer et al. (1987, 1989) showed that any concept class that is learnab...
research
10/05/2022

Multiclass Learnability Beyond the PAC Framework: Universal Rates and Partial Concept Classes

In this paper we study the problem of multiclass classification with a b...
research
07/11/2020

A Computational Separation between Private Learning and Online Learning

A recent line of work has shown a qualitative equivalence between differ...
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
07/18/2021

A Theory of PAC Learnability of Partial Concept Classes

We extend the theory of PAC learning in a way which allows to model a ri...
research
03/15/2022

Approximability and Generalisation

Approximate learning machines have become popular in the era of small de...
research
09/19/2013

Predictive PAC Learning and Process Decompositions

We informally call a stochastic process learnable if it admits a general...

Please sign up or login with your details

Forgot password? Click here to reset