Sparse Representations of Positive Functions via First and Second-Order Pseudo-Mirror Descent

Sparse Representations of Positive Functions via First and Second-Order Pseudo-Mirror Descent

We consider expected risk minimization problems when the range of the estimator is required to be nonnegative, motivated by the settings of maximum likelihood estimation (MLE) and trajectory optimization. To facilitate nonlinear interpolation, we hypothesize that the search space is a Reproducing Ke...

Full description

Bibliographic Details
Main Authors: Chakraborty, A. (Author), Koppel, A. (Author), Rajawat, K. (Author)
Format: Article
Language:English
Published: Institute of Electrical and Electronics Engineers Inc. 2022
Subjects:
Budget control
Complexity theory
Convergence
Eigenvalues and eigenfunctions
First order
Kernel
Maximum likelihood estimation
Mirrors
Pseudo gradients
Random processes
Reproducing Kernel Hilbert spaces
Risk management
Risk perception
Risks management
Second orders
Sparse representation
Stochastic processes
Stochastic systems
Training
Via-first
Online Access:View Fulltext in Publisher

Internet

View Fulltext in Publisher

Similar Items