Stochastic Gradient Descent Performs Variational Inference, Converges to Limit Cycles for Deep Networks.

Pratik Chaudhari Stefano Soatto

Published in: ITA (2018)

Keyphrases

stochastic gradient descent
least squares
step size
bayesian inference
loss function
regularization parameter
machine learning
posterior distribution
support vector machine
prior knowledge
active learning
parameter estimation
random variables
closed form
prior information