Adaptive learning rates and parallelization for stochastic, sparse, non-smooth gradients

Tom Schaul Yann LeCun

Published in: ICLR (Poster) (2013)

Keyphrases

learning rate
convergence rate
gaussian kernels
covering numbers
learning algorithm
uniform convergence
neural network
multi objective
high dimensional
data mining
machine learning
genetic algorithm
global optimization
convergence speed
convergence theorem