Sample-efficient Strategies for Learning in the Presence of Noise

N. Cesa-Bianchi, E. Dichterman, Paul Fischer, E. Shamir, H.-U. Simon

    Research output: Contribution to journalJournal articleResearchpeer-review


    In this paper, we prove various results about PAC learning in the presence of malicious noise. Our main interest is the sample size behavior of learning algorithms. We prove the first nontrivial sample complexity lower bound in this model by showing that order of &egr;/&Dgr;2 + d/&Dgr; (up to logarithmic factors) examples are necessary for PAC learning any target class of {#123;0,1}#125;-valued functions of VC dimension d, where &egr; is the desired accuracy and &eegr; = &egr;/(1 + &egr;) - &Dgr; the malicious noise rate (it is well known that any nontrivial target class cannot be PAC learned with accuracy &egr; and malicious noise rate &eegr; &egr;/(1 + &egr;), this irrespective to sample complexity). We also show that this result cannot be significantly improved in general by presenting efficient learning algorithms for the class of all subsets of d elements and the class of unions of at most d intervals on the real line. This is especialy interesting as we can also show that the popular minimum disagreement strategy needs samples of size d &egr;/&Dgr;2, hence is not optimal with respect to sample size. We then discuss the use of randomized hypotheses. For these the bound &egr;/(1 + &egr;) on the noise rate is no longer true and is replaced by 2&egr;/(1 + 2&egr;). In fact, we present a generic algorithm using randomized hypotheses that can tolerate noise rates slightly larger than &egr;/(1 + &egr;) while using samples of size d/&egr; as in the noise-free case. Again one observes a quadratic powerlaw (in this case d&egr;/&Dgr;2, &Dgr; = 2&egr;/(1 + 2&egr;) - &eegr;) as &Dgr; goes to zero. We show upper and lower bounds of this order.
    Original languageEnglish
    JournalJournal of the ACM
    Issue number5
    Pages (from-to)684-719
    Publication statusPublished - 1999

    Fingerprint Dive into the research topics of 'Sample-efficient Strategies for Learning in the Presence of Noise'. Together they form a unique fingerprint.

    Cite this