Learning a tree-structured Ising model in order to make predictions (Q2196190)

From MaRDI portal
scientific article
Language Label Description Also known as
English
Learning a tree-structured Ising model in order to make predictions
scientific article

    Statements

    Learning a tree-structured Ising model in order to make predictions (English)
    0 references
    0 references
    0 references
    28 August 2020
    0 references
    The objective of this paper is to show that learning a model that makes accurate predictions is possible even when structure learning is not. For realizing of this objective, the authors introduced a loss function to evaluate learning algorithms based on the accuracy of low-order marginals. The small-set total variation between true distribution \(P\) and learned distribution \(Q\) is used. The main result gives lower and upper bounds on the number of samples needed to learn a tree Ising model to ensure small \(L^{(2)}\) loss, which in this setting is equivalent to accurate pairwise marginals. In fact, the main result concerns the maximum likelihood tree (also called Chow-Liu tree, see [\textit{C. K. Chow} and \textit{C. N. Liu}, IEEE Trans. Inf. Theory 14, 462--467 (1968; Zbl 0165.22305)]. At the end of the paper, some interesting numerical simulations to demonstrate the performance of the Chow-Liu algorithm in terms of both the probability of incorrect recovery of underlying structure (zero-one loss) and the \(L^{(2)}\) loss are presented.
    0 references
    0 references
    high-dimensional statistics
    0 references
    model selection
    0 references
    Markov random fields
    0 references
    Ising model
    0 references
    prediction
    0 references
    tree model
    0 references
    maximum likelihood tree
    0 references
    Chow-Liu tree
    0 references
    0 references
    0 references
    0 references
    0 references
    0 references
    0 references
    0 references
    0 references
    0 references
    0 references
    0 references

    Identifiers

    0 references
    0 references
    0 references
    0 references
    0 references
    0 references
    0 references
    0 references
    0 references