Regular Article
Robust Learning Aided by Context

https://doi.org/10.1006/jcss.1999.1637Get rights and content
Under an Elsevier user license
open archive

Abstract

Empirical studies of multitask learning provide some evidence that the performance of a learning system on its intended targets improves by presenting to the learning system related tasks, also called contexts, as additional input. Angluin, Gasarch, and Smith, as well as Kinber, Smith, Velauthapillai, and Wiehagen, have provided mathematical justification for this phenomenon in the inductive inference framework. However, their proofs rely heavily on self-referential coding tricks; that is, they directly code the solution of the learning problem into the context. Fulk has shown that for the Ex- and Bc-anomaly hierarchies, such results, which rely on self-referential coding tricks, do not hold robustly. In this work we analyze robust versions of learning aided by context and show that—in contrast to Fulk's result above—context also aids learning robustly. Also studied is the difficulty of the functional dependence between the intended target tasks and useful associated contexts.

Cited by (0)

Most of this work was carried out while J. Case, S. Jain, M. Ott, and F. Stephan were visiting the School of Computer Science and Engineering at the University of New South Wales.

Supported by the Deutsche Forschungsgemeinschaft (DFG) Graduiertenkolleg “Beherrschbarkeit komplexer Systeme” (GRK 209/2-96).

Supported by Australian Research Council Grant A49600456.

§

Supported by the Deutsche Forschungsgemeinschaft (DFG) Grant Am 60/9-1.

f1

E-mail: [email protected]

f2

E-mail: [email protected]

f3

E-mail: [email protected]

f4

E-mail: [email protected]

f5

E-mail: [email protected]