Benign Underfitting of Stochastic Gradient Descent.
Tomer KorenRoi LivniYishay MansourUri ShermanPublished in: NeurIPS (2022)
Keyphrases
- stochastic gradient descent
- least squares
- loss function
- matrix factorization
- step size
- regularization parameter
- support vector machine
- random forests
- online algorithms
- multiple kernel learning
- weight vector
- linear combination
- importance sampling
- small number
- image restoration
- collaborative filtering
- missing data
- machine learning methods