New d-separation identification results for learning continuous latent variable models

ABSTRACT

Learning the structure of graphical models is an important task, but one of considerable difficulty when latent variables are involved. Because conditional independences using hidden variables cannot be directly observed, one has to rely on alternative methods to identify the d-separations that define the graphical structure. This paper describes new distribution-free techniques for identifying d-separations in continuous latent variable models when non-linear dependencies are allowed among hidden variables.

REFERENCES

• 1: Bach, F., & Jordan, M. (2002). Learning graphical models with Mereer kernels. Neural Information Processing Systems.
• 2: D. J. Bartholomew, Latent variable models and factors analysis, Oxford University Press, Inc., New York, NY, 1987
• 3: Bishop, C. (1998). Latent variable models. Learning in Graphical Models.
• 4: Bollen, K. (1989). Structural Equation Models with Latent Variables. John Wiley & Sons.
• 5: Carroll, R., Ruppert, D., & Stefanski, L. (1995). Measurement Error in Nonlinear Models. Chapman & Hall.
• 6: David Maxwell Chickering, Optimal structure identification with greedy search, The Journal of Machine Learning Research, 3, p.507-554, 3/1/2003 [doi>10.1162/153244303321897717]
• 7: Ghahramani, Z., & Hinton, G. (1996). The EM algorithm for the mixture of factor analyzers. Technical Report CRG-TR-96-1. Department of Computer Science, University of Toronto.
• 8: Iftach Nachman , Gal Elidan , Nir Friedman, "Ideal Parent" structure learning for continuous variable networks, Proceedings of the 20th conference on Uncertainty in artificial intelligence, p.400-409, July 07-11, 2004, Banff, Canada
• 9: Judea Pearl, Causality: models, reasoning, and inference, Cambridge University Press, New York, NY, 2000
• 10: Silva, R., & Scheines, R. (2005). New d-separation identification results for learning continuous latent variable models. Technical Report CMU-CALD-05-104, Carnegie Mellon University.
• 11: Silva, R., Scheines, R., Glymour, C., & Spirtes, P. (2003). Learning measurement models for unobserved variables. Proceedings of 19th Conference on Uncertainty in Artificial Intelligence, 543--550.
• 12: Silva, R., Scheines, R., Glymour, C., & Spirtes, P. (2005). Learning the structure of linear latent variable models. Submitted.
• 13: Spirtes, P., Glymour, C., & Scheines, R. (2000). Causation, Prediction and Search. Cambridge University Press.
• 14: Tian, J., & Pearl, J. (2002). On the testable implications of causal models with hidden variables. Proceedings of the 18th Conference on Uncertainty in Artificial Intelligence.