Gradient descent - Revision history

Karl Jones at 02:38, 13 October 2016

2016-10-13T02:38:46Z

Karl Jones at 02:37, 13 October 2016

2016-10-13T02:37:30Z

Karl Jones at 02:36, 13 October 2016

2016-10-13T02:36:09Z

Karl Jones: Created page with "'''Gradient descent''' is a first-order iterative optimization algorithm. == Description == To find a local minimum of a function using gradie..."

2016-10-13T02:31:29Z

Created page with "'''Gradient descent''' is a first-order iterative optimization algorithm. == Description == To find a local minimum of a function using gradie..."

New page

'''Gradient descent''' is a [[First-order method|first-order]] [[iterative]] optimization [[algorithm]].

== Description ==

To find a local minimum of a function using gradient descent, one takes steps proportional to the negative of the gradient (or of the approximate gradient) of the function at the current point. If instead one takes steps proportional to the positive of the gradient, one approaches a local maximum of that function; the procedure is then known as gradient ascent.

Gradient descent is also known as steepest descent, or the method of steepest descent. Gradient descent should not be confused with the method of steepest descent for approximating integrals.

== See also ==

* [[BFGS method]]
* [[Conjugate gradient method]]
* [[Delta rule]]
* [[First-order method]]
* [[Nelder–Mead method]]
* [[Preconditioning]]
* [[Rprop]]
* [[Stochastic gradient descent]]
* [[Wolfe conditions]]

== External links ==

* [https://en.wikipedia.org/wiki/Gradient_descent Gradient descent] @ Wikipedia

[[Category:Mathematics]]

@@ Line 1: / Line 1: @@
-'''Gradient descent''' is a [[First-order method|first-order]] [[Iterative method|iterative]] optimization [[algorithm]].
+'''Gradient descent''' is a [[First-order method|first-order]] [[Iterative method|iterative]] [[Mathematical optimization|optimization]] [[algorithm]].
 == Description ==
@@ Line 14: / Line 14: @@
 * [[First-order method]]
 * [[Iterative method]]
 * [[Nelder–Mead method]]
 * [[Preconditioning]]

@@ Line 3: / Line 3: @@
 == Description ==
-To find a local minimum of a function using gradient descent, one takes steps proportional to the negative of the gradient (or of the approximate gradient) of the function at the current point. If instead one takes steps proportional to the positive of the gradient, one approaches a local maximum of that function; the procedure is then known as gradient ascent.
+To find a local minimum of a function using gradient descent, one takes steps proportional to the negative of the [[gradient]] (or of the approximate gradient) of the function at the current point. If instead one takes steps proportional to the positive of the gradient, one approaches a local maximum of that function; the procedure is then known as gradient ascent.
-Gradient descent is also known as steepest descent, or the method of steepest descent. Gradient descent should not be confused with the method of steepest descent for approximating integrals.
+Gradient descent is also known as steepest descent, or the method of steepest descent.
 == See also ==
@@ Line 13: / Line 15: @@
 * [[Delta rule]]
 * [[First-order method]]
 * [[Iterative method]]
 * [[Mathematical optimization]]