A Unified View of Regularized Dual Averaging and Mirror Descent with Implicit Updates

Computer Science – Learning

Scientific paper

Rate now

  [ 0.00 ] – not rated yet Voters 0   Comments 0

Details

Extensively updated version of earlier draft with new analysis including a general treatment of composite objectives and exper

Scientific paper

We study three families of online convex optimization algorithms: follow-the-proximally-regularized-leader (FTRL-Proximal), regularized dual averaging (RDA), and composite-objective mirror descent. We first prove equivalence theorems that show all of these algorithms are instantiations of a general FTRL update. This provides theoretical insight on previous experimental observations. In particular, even though the FOBOS composite mirror descent algorithm handles L1 regularization explicitly, it has been observed that RDA is even more effective at producing sparsity. Our results demonstrate that FOBOS uses subgradient approximations to the L1 penalty from previous rounds, leading to less sparsity than RDA, which handles the cumulative penalty in closed form. The FTRL-Proximal algorithm can be seen as a hybrid of these two, and outperforms both on a large, real-world dataset. Our second contribution is a unified analysis which produces regret bounds that match (up to logarithmic terms) or improve the best previously known bounds. This analysis also extends these algorithms in two important ways: we support a more general type of composite objective and we analyze implicit updates, which replace the subgradient approximation of the current loss function with an exact optimization.

No associations

LandOfFree

Say what you really think

Search LandOfFree.com for scientists and scientific papers. Rate them and share your experience with other people.

Rating

A Unified View of Regularized Dual Averaging and Mirror Descent with Implicit Updates does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.

If you have personal experience with A Unified View of Regularized Dual Averaging and Mirror Descent with Implicit Updates, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and A Unified View of Regularized Dual Averaging and Mirror Descent with Implicit Updates will most certainly appreciate the feedback.

Rate now

     

Profile ID: LFWR-SCP-O-28116

  Search
All data on this website is collected from public sources. Our data reflects the most accurate information available at the time of publication.