翻訳と辞書
Words near each other
・ Gradež, Velike Lašče
・ Grade–Ruan
・ Gradgrind
・ Gradhiva
・ Gradian
・ Gradiant (Galician Research and Development Center in Advanced Telecommunications)
・ Gradiconus
・ Gradidge
・ Gradient
・ Gradient (disambiguation)
・ Gradient analysis
・ Gradient Analytics
・ Gradient boosting
・ Gradient conjecture
・ Gradient copolymers
Gradient descent
・ Gradient Domain Image Processing
・ Gradient enhanced NMR spectroscopy
・ Gradient method
・ Gradient multilayer nanofilm
・ Gradient network
・ Gradient noise
・ Gradient oven tester
・ Gradient pattern analysis
・ Gradient Salience Model
・ Gradient theorem
・ Gradient well-formedness
・ Gradient-index optics
・ Gradient-like vector field
・ Gradient-related


Dictionary Lists
翻訳と辞書 辞書検索 [ 開発暫定版 ]
スポンサード リンク

Gradient descent : ウィキペディア英語版
Gradient descent

Gradient descent is a first-order optimization algorithm. 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. However, gradient descent should not be confused with the method of steepest descent for approximating integrals.
==Description==

Gradient descent is based on the observation that if the multivariable function F(\mathbf) is defined and differentiable in a neighborhood of a point \mathbf, then F(\mathbf) decreases ''fastest'' if one goes from \mathbf in the direction of the negative gradient of F at \mathbf, -\nabla F(\mathbf). It follows that, if
: \mathbf = \mathbf-\gamma\nabla F(\mathbf)
for \gamma small enough, then F(\mathbf)\geq F(\mathbf). With this observation in mind, one starts with a guess \mathbf_0 for a local minimum of F, and considers the sequence
\mathbf_0, \mathbf_1, \mathbf_2, \dots such that
:\mathbf_=\mathbf_n-\gamma_n \nabla F(\mathbf_n),\ n \ge 0.
We have
:F(\mathbf_0)\ge F(\mathbf_1)\ge F(\mathbf_2)\ge \cdots,
so hopefully the sequence (\mathbf_n) converges to the desired local minimum. Note that the value of the ''step size'' \gamma is allowed to change at every iteration. With certain assumptions on the function F (for example, F convex and \nabla F Lipschitz) and particular choices of \gamma (e.g., chosen via a line search that satisfies the Wolfe conditions), convergence to a local minimum can be guaranteed. When the function F is convex, all local minima are also global minima, so in this case gradient descent can converge to the global solution.
This process is illustrated in the picture to the right. Here F is assumed to be defined on the plane, and that its graph has a bowl shape. The blue curves are the contour lines, that is, the regions on which the value of F is constant. A red arrow originating at a point shows the direction of the negative gradient at that point. Note that the (negative) gradient at a point is orthogonal to the contour line going through that point. We see that gradient ''descent'' leads us to the bottom of the bowl, that is, to the point where the value of the function F is minimal.

抄文引用元・出典: フリー百科事典『 ウィキペディア(Wikipedia)
ウィキペディアで「Gradient descent」の詳細全文を読む



スポンサード リンク
翻訳と辞書 : 翻訳のためのインターネットリソース

Copyright(C) kotoba.ne.jp 1997-2016. All Rights Reserved.