Skip to main content

Provable learning of noisy-or networks

Author(s): Arora, Sanjeev; Ge, R; Ma, T; Risteski, A

Download
To refer to this page use: http://arks.princeton.edu/ark:/88435/pr1n431
Full metadata record
DC FieldValueLanguage
dc.contributor.authorArora, Sanjeev-
dc.contributor.authorGe, R-
dc.contributor.authorMa, T-
dc.contributor.authorRisteski, A-
dc.date.accessioned2019-08-29T17:05:05Z-
dc.date.available2019-08-29T17:05:05Z-
dc.date.issued2017en_US
dc.identifier.citationArora, S, Ge, R, Ma, T, Risteski, A. (2017). Provable learning of noisy-or networks. Part F128415 (1057 - 1066. doi:10.1145/3055399.3055482en_US
dc.identifier.urihttp://arks.princeton.edu/ark:/88435/pr1n431-
dc.description.abstractMany machine learning applications use latent variable models to explain structure in data, whereby visible variables (= coordinates of the given datapoint) are explained as a probabilistic function of some hidden variables. Finding parameters with the maximum likelihood is NP-hard even in very simple settings. In recent years, provably efficient algorithms were nevertheless developed for models with linear structures: topic models, mixture models, hidden Markov models, etc. These algorithms use matrix or tensor decomposition, and make some reasonable assumptions about the parameters of the underlying model. But matrix or tensor decomposition seems of little use when the latent variable model has nonlinearities. The current paper shows how to make progress: tensor decomposition is applied for learning the single-layer noisy or network, which is a textbook example of a Bayes net, and used for example in the classic QMR-DT software for diagnosing which disease(s) a patient may have by observing the symptoms he/she exhibits. The technical novelty here, which should be useful in other settings in future, is analysis of tensor decomposition in presence of systematic error (i.e., where the noise/error is correlated with the signal, and doesn't decrease as number of samples goes to infinity). This requires rethinking all steps of tensor decomposition methods from the ground up. For simplicity our analysis is stated assuming that the network parameters were chosen from a probability distribution but the method seems more generally applicable.en_US
dc.format.extent1057 - 1066en_US
dc.language.isoen_USen_US
dc.relation.ispartofProceedings of the Annual ACM Symposium on Theory of Computingen_US
dc.rightsAuthor's manuscripten_US
dc.titleProvable learning of noisy-or networksen_US
dc.typeConference Articleen_US
dc.identifier.doidoi:10.1145/3055399.3055482-
pu.type.symplectichttp://www.symplectic.co.uk/publications/atom-terms/1.0/conference-proceedingen_US

Files in This Item:
File Description SizeFormat 
Provable learning of Noisy-or Networks.pdf373.79 kBAdobe PDFView/Download


Items in OAR@Princeton are protected by copyright, with all rights reserved, unless otherwise indicated.