Trial and Error: A new Approach to Space-Bounded Learning

F. Ameur, Paul Fischer, H.-U. Hoeffgen, F. Meyer auf der Heide

    Research output: Contribution to journalJournal articleResearchpeer-review


    A pac-learning algorithm is d-space bounded, if it stores at most d examples from the sample at any time. We characterize the d-space learnable concept classes. For this purpose we introduce the compression parameter of a concept class 𝒞 and design our trial and error learning algorithm. We show: 𝒞 is d-space learnable if and only if the compression parameter of 𝒞 is at most d. This learning algorithm does not produce a hypothesis consistent with the whole sample as previous approaches, for example, by Floyd, who presents consistent space bounded learning algorithms, but has to restrict herself to very special concept classes. On the other hand our algorithm needs large samples; the compression parameter appears as exponent in the sample size. We present several examples of polynomial time space bounded learnable concept classes: all intersection closed concept classes with finite VC-dimension; convex n-gons in R/sup 2/ ; halfspaces in R/sup n/ ; unions of triangles in R/sup 2/ . We further relate the compression parameter to the VC-dimension, and discuss variants of this parameter
    Original languageEnglish
    JournalActa Informatica
    Issue number7
    Pages (from-to)621-631
    Publication statusPublished - 1996


    Dive into the research topics of 'Trial and Error: A new Approach to Space-Bounded Learning'. Together they form a unique fingerprint.

    Cite this