mini-batch size
New Insight into Hybrid Stochastic Gradient Descent: Beyond With-Replacement Sampling and Convexity
Pan Zhou, Xiaotong Yuan, Jiashi Feng
Neural Information Processing Systems http://nips.cc/
Country:
- Asia > China > Jiangsu Province > Nanjing (0.04)
- North America > Canada > Quebec > Montreal (0.04)
- Asia > Singapore > Central Region > Singapore (0.04)
- Asia > Middle East > Jordan (0.04)
Technology: Information Technology > Artificial Intelligence > Machine Learning > Statistical Learning > Gradient Descent (1.00)
Country:
- South America > Paraguay > Asunción > Asunción (0.04)
- North America > Canada (0.04)
- Europe > France > Île-de-France (0.04)
Technology: Information Technology > Artificial Intelligence > Machine Learning > Statistical Learning (0.70)
Non-asymptotic Analysis of Stochastic Methods for Non-Smooth Non-Convex Regularized Problems
Stochastic Proximal Gradient (SPG) methods have been widely used for solving optimization problems with a simple (possibly non-smooth) regularizer in machine learning and statistics.
Country:
- North America > United States > Massachusetts > Middlesex County > Cambridge (0.04)
- North America > Canada > British Columbia > Metro Vancouver Regional District > Vancouver (0.04)
Technology: Information Technology > Artificial Intelligence > Machine Learning > Statistical Learning (0.48)
Country:
- North America > Canada > British Columbia > Vancouver (0.04)
- North America > United States > Massachusetts > Middlesex County > Cambridge (0.04)
- North America > United States > California > San Diego County > San Diego (0.04)
- (3 more...)
Technology: Information Technology > Artificial Intelligence > Machine Learning > Neural Networks (0.72)
SupplementaryMaterial
Asstated in Section 2, most GNNs can be interpreted as performing message passing on node features, followed by feature transformation and an activation function (Eq.
