Open Problem: Tight Convergence of SGD in Constant Dimension.

Tomer Koren Shahar Segal

Published in: COLT (2020)

Keyphrases

upper bound
worst case
stochastic gradient descent
convergence rate
lower bound
update rule
neural network
convergence speed
initial conditions
multiple dimensions
database
cost function
evolutionary algorithm
iterative algorithms
global convergence
real time
convergence analysis