Abstract
We describe a new iterative method for parameter estimation of Gaussian mixtures. The new method is based on a framework developed by Kivinen and Warmuth for supervised on-line learning. In contrast to gradient descent and EM, which estimate the mixture's covariance matrices, the proposed method estimates the inverses of the covariance matrices. Furthermore, the new parameter estimation procedure can be applied in both on-line and batch settings. We show experimentally that it is typically faster than EM, and usually requires about half as many iterations as EM.
| Original language | English (US) |
|---|---|
| Title of host publication | Advances in Neural Information Processing Systems 11 - Proceedings of the 1998 Conference, NIPS 1998 |
| Publisher | Neural information processing systems foundation |
| Pages | 578-584 |
| Number of pages | 7 |
| ISBN (Print) | 0262112450, 9780262112451 |
| State | Published - Jan 1 1999 |
| Externally published | Yes |
| Event | 12th Annual Conference on Neural Information Processing Systems, NIPS 1998 - Denver, CO, United States Duration: Nov 30 1998 → Dec 5 1998 |
Other
| Other | 12th Annual Conference on Neural Information Processing Systems, NIPS 1998 |
|---|---|
| Country | United States |
| City | Denver, CO |
| Period | 11/30/98 → 12/5/98 |
All Science Journal Classification (ASJC) codes
- Computer Networks and Communications
- Information Systems
- Signal Processing
Fingerprint Dive into the research topics of 'Batch and on-line parameter estimation of Gaussian mixtures based on the joint entropy'. Together they form a unique fingerprint.
Cite this
Singer, Y., & Warmuth, M. K. (1999). Batch and on-line parameter estimation of Gaussian mixtures based on the joint entropy. In Advances in Neural Information Processing Systems 11 - Proceedings of the 1998 Conference, NIPS 1998 (pp. 578-584). Neural information processing systems foundation.