Better Approximation and Faster Algorithm Using the Proximal Average

@inproceedings{Yu2013BetterAA,
  title={Better Approximation and Faster Algorithm Using the Proximal Average},
  author={Yaoliang Yu},
  booktitle={NIPS},
  year={2013}
}
It is a common practice to approximate “complicated” functions with more friendly ones. In large-scale machine learning applications, nonsmooth losses/regularizers that entail great computational challenges are usually approximated by smooth functions. We re-examine this powerful methodology and point out a nonsmooth approximation which simply pretends the linearity of the proximal map. The new approximation is justified using a recent convex analysis tool— proximal average, and yields a novel… CONTINUE READING
Highly Cited
This paper has 41 citations. REVIEW CITATIONS

2 Figures & Tables

Topics

Statistics

051015201620172018
Citations per Year

Citation Velocity: 10

Averaging 10 citations per year over the last 3 years.

Learn more about how we calculate this metric in our FAQ.