Probabilistic rule realization and selection

Haizi Yu, Tianxi Li, Lav R. Varshney

Research output: Contribution to journalConference articlepeer-review

3 Scopus citations


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
StatePublished - 2017
Externally publishedYes
Event31st Annual Conference on Neural Information Processing Systems, NIPS 2017 - Long Beach, United States
Duration: Dec 4 2017Dec 9 2017

Bibliographical note

Funding Information:
∗Equal contribution. †Supported in part by the IBM-Illinois Center for Cognitive Computing Systems Research (C3SR), a research collaboration as part of the IBM Cognitive Horizons Network.

Publisher Copyright:
© 2017 Neural information processing systems foundation. All rights reserved.


Dive into the research topics of 'Probabilistic rule realization and selection'. Together they form a unique fingerprint.

Cite this