Adaptive Subgradient Methods for Online Learning and Stochastic Optimization 论文

2011Journal of Machine Learning Research引用 313
Advanced Bandit Algorithms ResearchGaussian Processes and Bayesian InferenceStochastic Gradient Optimization Techniques

摘要

We present a new family of subgradient methods that dynamically incorporate knowledge of the geometry of the data observed in earlier iterations to perform more informative gradient-based learning....