Local Q-linear convergence and finite-time active set identification of ADMM on a class of penalized regression problems.
Elvis DohmatobMichael EickenbergBertrand ThirionGaël VaroquauxPublished in: ICASSP (2016)
Keyphrases
- regression problems
- active set
- linear regression
- genetic programming
- least squares
- cross validation
- efficient implementation
- learning machines
- convergence rate
- input space
- nonnegative matrix factorization
- feature selection
- maximum likelihood
- multi task
- image classification
- supervised learning
- support vector machine