(Choose 1 answer)
Suppose you are training a logistic regression classifier using stochastic gradient descent. You find that the
cost averaged over the last 500 examples, plotted as a function of the number of iterations, is slowly
increasing over time. Which of the following changes are likely to help?
A. Try averaging the cost over a smaller number of examples (say 250 examples instead of 500) in the plot.
B. Try averaging the cost over a larger number of examples (say 1000 examples instead of 500) in the plot
C. Try halving (decreasing) the learning rate, and see if that causes the cost to now consistently go down;and if not, keep halving it until it does.
D. Use fewer examples from your training set.
E46
