Asymptotic Analysis of Objectives based on Fisher Information in Active Learning.
Jamshid SouratiMurat AkçakayaTodd K. LeenDeniz ErdogmusJennifer G. DyPublished in: CoRR (2016)
Keyphrases
- asymptotic analysis
- fisher information
- active learning
- fluid model
- euclidean space
- information geometry
- positive definite
- probability density function
- noise level
- semi supervised
- learning algorithm
- geodesic distance
- machine learning
- neural network
- exponential family
- labeled data
- kernel function
- covariance matrix
- estimation error
- multidimensional scaling
- training set