A proximal gradient descent method with locally estimated step sizes is proposed and shown in experiments to outperform fixed-step proximal gradient descent on L1-regularized regression.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
math.OC 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Gradient Descent Methods for Regularized Optimization
A proximal gradient descent method with locally estimated step sizes is proposed and shown in experiments to outperform fixed-step proximal gradient descent on L1-regularized regression.