✦ LIBER ✦

Learning rates of gradient descent algorithm for classification

✍ Scribed by Xue-Mei Dong; Di-Rong Chen

Book ID: 104005899
Publisher: Elsevier Science
Year: 2009
Tongue: English
Weight: 702 KB
Volume: 224
Category: Article
ISSN: 0377-0427
DOI: 10.1016/j.cam.2008.04.022

No coin nor oath required. For personal study only.

✦ Synopsis

In this paper, a stochastic gradient descent algorithm is proposed for the binary classification problems based on general convex loss functions. It has computational superiority over the existing algorithms when the sample size is large. Under some reasonable assumptions on the hypothesis space and the underlying distribution, the learning rate of the algorithm has been established, which is faster than that of closely related algorithms.

📜 SIMILAR VOLUMES

Online Gradient Descent Learning Algorit

Online Gradient Descent Learning Algorithms

✍ Yiming Ying; Massimiliano Pontil 📂 Article 📅 2007 🏛 Springer-Verlag 🌐 English ⚖ 603 KB

On the momentum term in gradient descent

On the momentum term in gradient descent learning algorithms

✍ Ning Qian 📂 Article 📅 1999 🏛 Elsevier Science 🌐 English ⚖ 311 KB

Momentum-weighted conjugate gradient des

Momentum-weighted conjugate gradient descent algorithm for gradient coil optimization

✍ Hanbing Lu; Andrzej Jesmanowicz; Shi-Jiang Li; James S. Hyde 📂 Article 📅 2003 🏛 John Wiley and Sons 🌐 English ⚖ 164 KB

## Abstract MRI gradient coil design is a type of nonlinear constrained optimization. A practical problem in transverse gradient coil design using the conjugate gradient descent (CGD) method is that wire elements move at different rates along orthogonal directions (__r, φ, z__), and tend to cross,

Efficient gradient descent method of RBF

Efficient gradient descent method of RBF neural entworks with adaptive learning rate

✍ Jiayu Lin; Ying Liu 📂 Article 📅 2002 🏛 SP Science Press 🌐 English ⚖ 198 KB

Convergence analysis of gradient descent

Convergence analysis of gradient descent stochastic algorithms

✍ A. Shapiro; Y. Wardi 📂 Article 📅 1996 🏛 Springer 🌐 English ⚖ 765 KB

Some considerations on conventional neur

Some considerations on conventional neuro-fuzzy learning algorithms by gradient descent method

✍ Yan Shi; Masaharu Mizumoto 📂 Article 📅 2000 🏛 Elsevier Science 🌐 English ⚖ 232 KB

In this paper, we try to analyze several conventional neuro-fuzzy learning algorithms, which are widely used in recent fuzzy applications for tuning fuzzy rules, and give a summarization of their properties in detail. Some of these properties show that the uses of the conventional neuro-fuzzy learni