Learning Rate Schedules in the Presence of Distribution Shift.

Matthew Fahrbach Adel Javanmard Vahab Mirrokni Pratik Worah

Published in: ICML (2023)

Keyphrases

learning rate
convergence rate
learning algorithm
error function
convergence speed
adaptive learning rate
multilayer neural networks
scheduling problem
hidden layer
training algorithm
natural gradient
rapid convergence
activation function
convergence theorem
data mining
state space
bp neural network algorithm