Empirical Risk Minimization with Approximations of Probabilistic Grammars

S. B. Cohen; N. A. Smith

Empirical Risk Minimization with Approximations of Probabilistic Grammars

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

Probabilistic grammars are generative statistical models that are useful for compositional and sequential structures. We present a framework, reminiscent of structural risk minimization, for empirical risk minimization of the parameters of a fixed probabilistic grammar using the log-loss. We derive sample complexity bounds in this framework that apply both to the supervised setting and the unsupervised setting.

Original language	English
Title of host publication	Proceedings of NIPS
Publisher	NIPS Foundation
Pages	1-9
Number of pages	9
Publication status	Published - 2010

Access to Document

NIPS2010_0803Final published version, 245 KB

Fingerprint Dive into the research topics of 'Empirical Risk Minimization with Approximations of Probabilistic Grammars'. Together they form a unique fingerprint.

Cite this

@inproceedings{c56808b9ccaa467fb50d81979b1b0e8e,

title = "Empirical Risk Minimization with Approximations of Probabilistic Grammars",

abstract = "Probabilistic grammars are generative statistical models that are useful for compositional and sequential structures. We present a framework, reminiscent of structural risk minimization, for empirical risk minimization of the parameters of a fixed probabilistic grammar using the log-loss. We derive sample complexity bounds in this framework that apply both to the supervised setting and the unsupervised setting. ",

author = "Cohen, {S. B.} and Smith, {N. A.}",

year = "2010",

language = "English",

pages = "1--9",

booktitle = "Proceedings of NIPS",

publisher = "NIPS Foundation",

}

TY - GEN

T1 - Empirical Risk Minimization with Approximations of Probabilistic Grammars

AU - Cohen, S. B.

AU - Smith, N. A.

PY - 2010

Y1 - 2010

N2 - Probabilistic grammars are generative statistical models that are useful for compositional and sequential structures. We present a framework, reminiscent of structural risk minimization, for empirical risk minimization of the parameters of a fixed probabilistic grammar using the log-loss. We derive sample complexity bounds in this framework that apply both to the supervised setting and the unsupervised setting.

AB - Probabilistic grammars are generative statistical models that are useful for compositional and sequential structures. We present a framework, reminiscent of structural risk minimization, for empirical risk minimization of the parameters of a fixed probabilistic grammar using the log-loss. We derive sample complexity bounds in this framework that apply both to the supervised setting and the unsupervised setting.

M3 - Conference contribution

SP - 1

EP - 9

BT - Proceedings of NIPS

PB - NIPS Foundation

ER -