This thesis presents a family of adaptive curvature methods for gradient-based stochastic optimization. In particular, a general algorithmic framework is introduced along with a practical implementation that yields an efficient, adaptive curvature gradient descent algorithm. To this end, a theoretical and practical link between curvature matrix estimation and shrinkage methods for covariance matrices is established. The use of shrinkage improves estimation accuracy of the curvature matrix when data samples are scarce.
Download count: 0
- Partial requirement for: M.S., Arizona State University, 2019Note typethesis
- Includes bibliographical references (pages 35-39)Note typebibliography
- Field of study: Computer science