Probabilistic rule realization and selection

Haizi Yu, Tianxi Li, Lav R Varshney

Research output: Contribution to journalConference article

Abstract

Abstaction and realization are bilateral processes that are key in deriving intelligence and creativity. In many domains, the two processes are approached through rules: high-level principles that reveal invariances within similar yet diverse examples. Under a probabilistic setting for discrete input spaces, we focus on the rule realization problem which generates input sample distributions that follow the given rules. More ambitiously, we go beyond a mechanical realization that takes whatever is given, but instead ask for proactively selecting reasonable rules to realize. This goal is demanding in practice, since the initial rule set may not always be consistent and thus intelligent compromises are needed. We formulate both rule realization and selection as two strongly connected components within a single and symmetric bi-convex problem, and derive an efficient algorithm that works at large scale. Taking music compositional rules as the main example throughout the paper, we demonstrate our model's efficiency in not only music realization (composition) but also music interpretation and understanding (analysis).

Original languageEnglish (US)
Pages (from-to)1563-1573
Number of pages11
JournalAdvances in Neural Information Processing Systems
Volume2017-December
StatePublished - Jan 1 2017
Event31st Annual Conference on Neural Information Processing Systems, NIPS 2017 - Long Beach, United States
Duration: Dec 4 2017Dec 9 2017

Fingerprint

Invariance
Chemical analysis

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Information Systems
  • Signal Processing

Cite this

Probabilistic rule realization and selection. / Yu, Haizi; Li, Tianxi; Varshney, Lav R.

In: Advances in Neural Information Processing Systems, Vol. 2017-December, 01.01.2017, p. 1563-1573.

Research output: Contribution to journalConference article

Yu, Haizi ; Li, Tianxi ; Varshney, Lav R. / Probabilistic rule realization and selection. In: Advances in Neural Information Processing Systems. 2017 ; Vol. 2017-December. pp. 1563-1573.
@article{b9c5c49249534a4197daa5509c00aa55,
title = "Probabilistic rule realization and selection",
abstract = "Abstaction and realization are bilateral processes that are key in deriving intelligence and creativity. In many domains, the two processes are approached through rules: high-level principles that reveal invariances within similar yet diverse examples. Under a probabilistic setting for discrete input spaces, we focus on the rule realization problem which generates input sample distributions that follow the given rules. More ambitiously, we go beyond a mechanical realization that takes whatever is given, but instead ask for proactively selecting reasonable rules to realize. This goal is demanding in practice, since the initial rule set may not always be consistent and thus intelligent compromises are needed. We formulate both rule realization and selection as two strongly connected components within a single and symmetric bi-convex problem, and derive an efficient algorithm that works at large scale. Taking music compositional rules as the main example throughout the paper, we demonstrate our model's efficiency in not only music realization (composition) but also music interpretation and understanding (analysis).",
author = "Haizi Yu and Tianxi Li and Varshney, {Lav R}",
year = "2017",
month = "1",
day = "1",
language = "English (US)",
volume = "2017-December",
pages = "1563--1573",
journal = "Advances in Neural Information Processing Systems",
issn = "1049-5258",

}

TY - JOUR

T1 - Probabilistic rule realization and selection

AU - Yu, Haizi

AU - Li, Tianxi

AU - Varshney, Lav R

PY - 2017/1/1

Y1 - 2017/1/1

N2 - Abstaction and realization are bilateral processes that are key in deriving intelligence and creativity. In many domains, the two processes are approached through rules: high-level principles that reveal invariances within similar yet diverse examples. Under a probabilistic setting for discrete input spaces, we focus on the rule realization problem which generates input sample distributions that follow the given rules. More ambitiously, we go beyond a mechanical realization that takes whatever is given, but instead ask for proactively selecting reasonable rules to realize. This goal is demanding in practice, since the initial rule set may not always be consistent and thus intelligent compromises are needed. We formulate both rule realization and selection as two strongly connected components within a single and symmetric bi-convex problem, and derive an efficient algorithm that works at large scale. Taking music compositional rules as the main example throughout the paper, we demonstrate our model's efficiency in not only music realization (composition) but also music interpretation and understanding (analysis).

AB - Abstaction and realization are bilateral processes that are key in deriving intelligence and creativity. In many domains, the two processes are approached through rules: high-level principles that reveal invariances within similar yet diverse examples. Under a probabilistic setting for discrete input spaces, we focus on the rule realization problem which generates input sample distributions that follow the given rules. More ambitiously, we go beyond a mechanical realization that takes whatever is given, but instead ask for proactively selecting reasonable rules to realize. This goal is demanding in practice, since the initial rule set may not always be consistent and thus intelligent compromises are needed. We formulate both rule realization and selection as two strongly connected components within a single and symmetric bi-convex problem, and derive an efficient algorithm that works at large scale. Taking music compositional rules as the main example throughout the paper, we demonstrate our model's efficiency in not only music realization (composition) but also music interpretation and understanding (analysis).

UR - http://www.scopus.com/inward/record.url?scp=85046993364&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85046993364&partnerID=8YFLogxK

M3 - Conference article

AN - SCOPUS:85046993364

VL - 2017-December

SP - 1563

EP - 1573

JO - Advances in Neural Information Processing Systems

JF - Advances in Neural Information Processing Systems

SN - 1049-5258

ER -