BriefGPT.xyz
Mar, 2016
优化目标的最优黑盒约减
Optimal Black-Box Reductions Between Optimization Objectives
HTML
PDF
Zeyuan Allen-Zhu, Elad Hazan
TL;DR
本研究提出了新的降维方法，可将一种机器学习方法应用于不同的光滑强凸度范围，不仅优化效果较好且实用性强，该方法在多个损失函数家族的线性分类器训练中展现出更快的运行速度和成功的实践应用。
Abstract
The diverse world of
machine learning
applications has given rise to a plethora of algorithms and
optimization methods
, finely tuned to the smoothness, convexity, and other parameterizations of the objective. In
→