My Account Log in

1 option

Generalized Stochastic Gradient Learning / George W. Evans, Seppo Honkapohja, Noah Williams.

NBER Working papers Available online

View online
Format:
Book
Author/Creator:
Evans, George W.
Contributor:
National Bureau of Economic Research.
Honkapohja, Seppo.
Williams, Noah.
Series:
Technical Working Paper Series (National Bureau of Economic Research) no. t0317.
NBER technical working paper series no. t0317
Language:
English
Physical Description:
1 online resource: illustrations (black and white);
Place of Publication:
Cambridge, Mass. National Bureau of Economic Research 2005.
Summary:
We study the properties of generalized stochastic gradient (GSG) learning in forward-looking models. We examine how the conditions for stability of standard stochastic gradient (SG) learning both differ from and are related to E-stability, which governs stability under least squares learning. SG algorithms are sensitive to units of measurement and we show that there is a transformation of variables for which E-stability governs SG stability. GSG algorithms with constant gain have a deeper justification in terms of parameter drift, robustness and risk sensitivity.
Notes:
Print version record
October 2005.

The Penn Libraries is committed to describing library materials using current, accurate, and responsible language. If you discover outdated or inaccurate language, please fill out this feedback form to report it and suggest alternative language.

Find

Home Release notes

My Account

Shelf Request an item Bookmarks Fines and fees Settings

Guides

Using the Find catalog Using Articles+ Using your account