On-Line Estimation with the Multivariate Gaussian Distribution
Lists
Only you see this
Abstract
We consider on-line density estimation with the multivariate Gaussian distribution. In each of a sequence of trials, the learner must posit a mean μ and covariance Σ; the learner then receives an instance x and incurs loss equal to the negative log-likelihood of x under the Gaussian density parameterized by (μ,Σ). We prove bounds on the regret for the follow-the-leader strategy, which amounts to choosing the sample mean and covariance of the previously seen data.
BibTeX
@inproceedings{dasgupta2007line,
author = {Sanjoy Dasgupta and Daniel J. Hsu},
title = {{On-Line Estimation with the Multivariate Gaussian Distribution}},
booktitle = {Conference on Learning Theory},
year = {2007},
doi = {10.1007/978-3-540-72927-3\_21},
}Loading related content...