Benchmark using svrg.update() vs putting the code directly inside sgd()

airoldilab / ai-sgd

Towards stability and optimality in stochastic gradient descent

5 stars 2 forks source link

Benchmark using svrg.update() vs putting the code directly inside sgd() #15

Open dustinvtran opened 9 years ago

dustinvtran commented 9 years ago

svrg.update() may possibly be slower due to loading in the entire DATA object per iteration of the main loop. This may be negligible unless the number of passes is arbitrarily large.