The Impact of Neural Network Overparameterization on Gradient Confusion and Stochastic Gradient Descent.
Karthik Abinav SankararamanSoham DeZheng XuW. Ronny HuangTom GoldsteinPublished in: ICML (2020)
Keyphrases
- stochastic gradient descent
- neural network
- least squares
- loss function
- matrix factorization
- step size
- support vector machine
- random forests
- back propagation
- weight vector
- genetic algorithm
- pairwise
- regularization parameter
- feature selection
- collaborative filtering
- learning algorithm
- multiple kernel learning
- importance sampling
- online algorithms