Dual Averaging Methods for Regularized Stochastic Learning and Online Optimization 论文

2010Journal of Machine Learning Research引用 235
Advanced Bandit Algorithms ResearchStochastic Gradient Optimization TechniquesDistributed Sensor Networks and Detection Algorithms

摘要

We consider regularized stochastic learning and online optimization problems, where the objective function is the sum of two convex terms: one is the loss function of the learning task, and the oth...