Data-Dependent Stability of Stochastic Gradient Descent.
Ilja KuzborskijChristoph H. LampertPublished in: CoRR (2017)
Keyphrases
- data dependent
- stochastic gradient descent
- loss function
- least squares
- matrix factorization
- step size
- random forests
- support vector machine
- multiple kernel learning
- regularization parameter
- weight vector
- online algorithms
- feature extraction
- learning algorithm
- support vector
- decision trees
- hash functions
- data sets
- computer vision
- cost function
- feature selection