• Corpus ID: 231632350

Screening for Sparse Online Learning

@article{Liang2021ScreeningFS,
  title={Screening for Sparse Online Learning},
  author={Jingwei Liang and Clarice Poon},
  journal={ArXiv},
  year={2021},
  volume={abs/2101.06982}
}
Sparsity promoting regularizers are widely used to impose low-complexity structure (e.g. `1-norm for sparsity) to the regression coefficients of supervised learning. In the realm of deterministic optimization, the sequence generated by iterative algorithms (such as proximal gradient descent) exhibit “finite activity identification”, namely, they can identify the low-complexity structure in a finite number of iterations. However, most online algorithms (such as proximal stochastic gradient… 

Figures from this paper