Stability of Stochastic Gradient Descent on Nonsmooth Convex Losses.
Raef BassilyVitaly FeldmanCristóbal GuzmánKunal TalwarPublished in: CoRR (2020)
Keyphrases
- stochastic gradient descent
- least squares
- loss function
- step size
- matrix factorization
- random forests
- weight vector
- regularization parameter
- multiple kernel learning
- support vector machine
- convex hull
- convex optimization
- importance sampling
- pairwise
- missing data
- feature space
- random forest
- convergence speed
- cost function