Probabilistic Rule Realization and Selection

Abstraction 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).

[1]  Jieping Ye,et al.  Two-Layer Feature Reduction for Sparse-Group Lasso via Decomposition of Convex Sets , 2014, NIPS.

[2]  Lav R. Varshney,et al.  Towards Deep Interpretability (MUS-ROVER II): Learning Hierarchical Representations of Tonal Music , 2017, ICLR.

[3]  Ranjitha Kumar,et al.  Learning Interpretable Musical Compositional Rules and Traces , 2016, ArXiv.

[4]  Birgit Wirtz,et al.  Visual Intelligence: Perception, Image, and Manipulation in Visual Communication , 1997 .

[5]  Lav R. Varshney,et al.  MUS-ROVER: A Self-Learning System for Musical Compositional Rules , 2016 .

[6]  Miguel Á. Carreira-Perpiñán,et al.  Projection onto the probability simplex: An efficient algorithm with a simple proof, and an application , 2013, ArXiv.

[7]  R. Tibshirani,et al.  Least angle regression , 2004, math/0406456.

[8]  R. Tibshirani,et al.  Strong rules for discarding predictors in lasso‐type problems , 2010, Journal of the Royal Statistical Society. Series B, Statistical methodology.

[9]  Pascal Vincent,et al.  Representation Learning: A Review and New Perspectives , 2012, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[10]  R. Tibshirani,et al.  Forward stagewise regression and the monotone lasso , 2007, 0705.0269.

[11]  David Cope An Expert System for Computer-Assisted Composition , 1987 .

[12]  Johann Joseph Fux,et al.  Gradus ad Parnassum , 1967 .

[13]  D. Jackson Interpretation of Inaccurate, Insufficient and Inconsistent Data , 1972 .

[14]  Kemal Ebcioglu,et al.  An Expert System for Harmonizing Four-Part Chorales , 1988, ICMC.

[15]  Dedre Gentner,et al.  ABSTRACTION PROCESSES DURING CONCEPT LEARNING: A STRUCTURAL VIEW , 2006 .

[16]  M. Yuan,et al.  Model selection and estimation in regression with grouped variables , 2006 .

[17]  Ken Haase,et al.  Discovery Systems: From AM to CYRANO , 1987 .

[18]  Zhi-Quan Luo,et al.  On the linear convergence of the alternating direction method of multipliers , 2012, Mathematical Programming.

[19]  Yoshua Bengio,et al.  Deep Learning of Representations: Looking Forward , 2013, SLSP.

[20]  R. Tibshirani,et al.  A note on the group lasso and a sparse group lasso , 2010, 1001.0736.

[21]  R. Tibshirani Regression Shrinkage and Selection via the Lasso , 1996 .

[22]  H. Zou,et al.  Regularization and variable selection via the elastic net , 2005 .

[23]  Stephen P. Boyd,et al.  Distributed Optimization and Statistical Learning via the Alternating Direction Method of Multipliers , 2011, Found. Trends Mach. Learn..