Statistical Optimality of Stochastic Gradient Descent on Hard Learning Problems through Multiple Passes.
Loucas Pillaud-VivienAlessandro RudiFrancis R. BachPublished in: CoRR (2018)
Keyphrases
- learning problems
- stochastic gradient descent
- multiple kernel learning
- learning algorithm
- learning tasks
- supervised learning
- kernel methods
- machine learning
- binary classification
- semi supervised learning
- machine learning algorithms
- reinforcement learning
- learning models
- loss function
- optimal solution
- prior knowledge
- unsupervised learning
- image segmentation
- multi task
- decision trees