An Interior-Point Stochastic Approximation Method and an L1-Regularized Delta Rule
Abstract
The stochastic approximation method is behind the solution to many important, actively-studied problems in machine learning. Despite its far-reaching application, there is almost no work on applying stochastic approximation to learning problems with constraints. The reason for this, we hypothesize, is that no robust, widely-applicable stochastic approximation method exists for handling such problems. We propose that interior-point methods are a natural solution. We establish the stability of a stochastic interior-point approximation method both analytically and empirically, and demonstrate its utility by deriving an on-line learning algorithm that also performs feature selection via L1 regularization.
Cite
Text
Carbonetto et al. "An Interior-Point Stochastic Approximation Method and an L1-Regularized Delta Rule." Neural Information Processing Systems, 2008.Markdown
[Carbonetto et al. "An Interior-Point Stochastic Approximation Method and an L1-Regularized Delta Rule." Neural Information Processing Systems, 2008.](https://mlanthology.org/neurips/2008/carbonetto2008neurips-interiorpoint/)BibTeX
@inproceedings{carbonetto2008neurips-interiorpoint,
title = {{An Interior-Point Stochastic Approximation Method and an L1-Regularized Delta Rule}},
author = {Carbonetto, Peter and Schmidt, Mark and Freitas, Nando D.},
booktitle = {Neural Information Processing Systems},
year = {2008},
pages = {233-240},
url = {https://mlanthology.org/neurips/2008/carbonetto2008neurips-interiorpoint/}
}