Skip to main content

Variational inference and model selection with generalized evidence bounds

Publication ,  Conference
Tao, C; Chen, L; Zhang, R; Henao, R; Carin, L
Published in: 35th International Conference on Machine Learning, ICML 2018
January 1, 2018

Recent advances on the scalability and flexibility of variational inference have made it successful at unravelling hidden patterns in complex data. In this work we propose a new variational bound formulation, yielding an estimator that extends beyond the conventional variational bound. It naturally subsumes the importance-weighted and Renyi bounds as special cases, and it is provably sharper than these counterparts. We also present an improved estimator for variational learning, and advocate a novel high signal-to-variance ratio update rule for the variational parameters. We discuss model-selection issues associated with existing evidence-lower-bound-based variational inference procedures, and show how to leverage the flexibility of our new formulation to address them. Empirical evidence is provided to validate our claims.

Duke Scholars

Published In

35th International Conference on Machine Learning, ICML 2018

ISBN

9781510867963

Publication Date

January 1, 2018

Volume

2

Start / End Page

1419 / 1435
 

Citation

APA
Chicago
ICMJE
MLA
NLM
Tao, C., Chen, L., Zhang, R., Henao, R., & Carin, L. (2018). Variational inference and model selection with generalized evidence bounds. In 35th International Conference on Machine Learning, ICML 2018 (Vol. 2, pp. 1419–1435).
Tao, C., L. Chen, R. Zhang, R. Henao, and L. Carin. “Variational inference and model selection with generalized evidence bounds.” In 35th International Conference on Machine Learning, ICML 2018, 2:1419–35, 2018.
Tao C, Chen L, Zhang R, Henao R, Carin L. Variational inference and model selection with generalized evidence bounds. In: 35th International Conference on Machine Learning, ICML 2018. 2018. p. 1419–35.
Tao, C., et al. “Variational inference and model selection with generalized evidence bounds.” 35th International Conference on Machine Learning, ICML 2018, vol. 2, 2018, pp. 1419–35.
Tao C, Chen L, Zhang R, Henao R, Carin L. Variational inference and model selection with generalized evidence bounds. 35th International Conference on Machine Learning, ICML 2018. 2018. p. 1419–1435.

Published In

35th International Conference on Machine Learning, ICML 2018

ISBN

9781510867963

Publication Date

January 1, 2018

Volume

2

Start / End Page

1419 / 1435