Accelerated Stochastic Gradient Descent for Minimizing Finite Sums.
Atsushi NitandaPublished in: AISTATS (2016)
Keyphrases
- stochastic gradient descent
- least squares
- loss function
- matrix factorization
- random forests
- step size
- regularization parameter
- support vector machine
- weight vector
- multiple kernel learning
- convergence rate
- online algorithms
- learning algorithm
- cost function
- objective function
- cross validation
- linear combination
- markov chain
- collaborative filtering
- importance sampling