On the Discrepancy Principle for Stochastic Gradient Descent.
Tim JahnBangti JinPublished in: CoRR (2020)
Keyphrases
- stochastic gradient descent
- least squares
- loss function
- matrix factorization
- step size
- random forests
- support vector machine
- regularization parameter
- weight vector
- multiple kernel learning
- similarity measure
- collaborative filtering
- optical flow
- closed form
- learning rate
- particle swarm optimization
- lower bound
- online algorithms
- machine learning