首页|New Machine Learning Study Findings Reported from University of Oslo (On the Gen eralization of Stochastic Gradient Descent With Momentum)
New Machine Learning Study Findings Reported from University of Oslo (On the Gen eralization of Stochastic Gradient Descent With Momentum)
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-Current study results on Machine Learn ing have been published. According to news reporting originating in Oslo, Norway , by NewsRx journalists, research stated, "While momentum-based accelerated vari ants of stochastic gradient descent (SGD) are widely used when training machine learning models, there is little theoretical understanding on the generalization error of such methods. In this work, we first show that there exists a convex l oss function for which the stability gap for multiple epochs of SGD with standar d heavy-ball momentum (SGDM) becomes unbounded." Funders for this research include Research Council of Norway, Research Council o f Norway, Hasler Foundation Program: Hasler Responsible AI, Swiss National Scien ce Foundation (SNSF), CGIAR.
OsloNorwayEuropeCyborgsEmerging TechnologiesMachine LearningUniversity of Oslo
NETL
NSTL
