Quantcast
Channel: Active questions tagged real-analysis - Mathematics Stack Exchange
Viewing all articles
Browse latest Browse all 9469

Can changing Gradient Descent step size/learing rate from constant 1/L to Armijo or exact line search change the convergence rate?

$
0
0

If instead of the classical $1/L$ constant step size we have adaptive step sizes chosen with exact line search or Armijo (let's say) can this alter the Big-O complexity of the convergence rate?

In Searching for Optimal Per Coordinate Step Sizes with Multidimensional Backtracking the authors note that"... even an exact line-search cannot improve the convergencerate beyond what is achievable with a fixed step-size".But this is for strongly convex functions - would the same be true in general non-convex case?


Viewing all articles
Browse latest Browse all 9469

Trending Articles



<script src="https://jsc.adskeeper.com/r/s/rssing.com.1596347.js" async> </script>