Tight Analyses for Non-Smooth Stochastic Gradient Descent.
Nicholas J. A. HarveyChristopher LiawYaniv PlanSikander RandhawaPublished in: CoRR (2018)
Keyphrases
- stochastic gradient descent
- least squares
- loss function
- matrix factorization
- step size
- lower bound
- online algorithms
- worst case
- random forests
- support vector machine
- upper bound
- weight vector
- importance sampling
- regularization parameter
- multiple kernel learning
- convergence rate
- image processing
- cost function
- evolutionary algorithm
- decision trees