Convergence of constant step stochastic gradient descent for non-smooth non-convex functions.
Pascal BianchiWalid HachemSholom SchechtmanPublished in: CoRR (2020)
Keyphrases
- stochastic gradient descent
- convex functions
- step size
- loss function
- convergence rate
- matrix factorization
- least squares
- random forests
- linear program
- convergence speed
- piecewise linear
- missing data
- regularization parameter
- convex sets
- support vector machine
- primal dual
- objective function
- machine learning
- multiple kernel learning
- special case