final_momentum parameter is never used

[jlmelville]

I don't think that the final momentum value is ever used. The momentum-decay line uses a hard-coded value of 0.85:

ft-SNE/tsne.py

Lines 186 to 187 in 4b5c368

	mom = float(get_epsilon(initial_momentum, lrDecay, epoch)) \
	if epoch < momentum_switch else 0.85

Appendix C of the paper mentions the learning rate and momentum decay but not the momentum switch, which would seem to force the momentum back up to a relatively large value for most of the optimization. Is the momentum decay useful in practice?