Interaction screening: Efficient and sample-optimal learning of ising models

Marc Vuffray, Sidhant Misra, Andrey Y. Lokhov, Michael Chertkov

    Результат исследований: Вклад в журналСтатья конференциирецензирование

    44 Цитирования (Scopus)


    We consider the problem of learning the underlying graph of an unknown Ising model on p spins from a collection of i.i.d. samples generated from the model. We suggest a new estimator that is computationally efficient and requires a number of samples that is near-optimal with respect to previously established information-theoretic lower-bound. Our statistical estimator has a physical interpretation in terms of "interaction screening". The estimator is consistent and is efficiently implemented using convex optimization. We prove that with appropriate regularization, the estimator recovers the underlying graph using a number of samples that is logarithmic in the system size p and exponential in the maximum coupling-intensity and maximum node-degree.

    Язык оригиналаАнглийский
    Страницы (с-по)2603-2611
    Число страниц9
    ЖурналAdvances in Neural Information Processing Systems
    СостояниеОпубликовано - 2016
    Событие30th Annual Conference on Neural Information Processing Systems, NIPS 2016 - Barcelona, Испания
    Продолжительность: 5 дек. 201610 дек. 2016


    Подробные сведения о темах исследования «Interaction screening: Efficient and sample-optimal learning of ising models». Вместе они формируют уникальный семантический отпечаток (fingerprint).