top | item 13817537

(no title)

amatsukawa | 9 years ago

It still scales O(N^2) in terms of computation though right?

discuss

order

eximius|9 years ago

If you save numerator_t and denominator_t from a previous computation, then h_t = f( (numerator_(t-1) + z + a) / (denominator_(t-1) + a) ). So it should be linear with t?

(where z and a are z(x_i, h_(i-1)), etc)

jostmey|9 years ago

Yes, I do save the numerator and denominator.

The model I used is: h_t = f( (numerator_(t-1) + z x e^a) / (denominator_(t-1) + e^a) )

Equations (7) in the arxiv link (here it is again: https://arxiv.org/pdf/1703.01253.pdf) provide the update equations. When implementing the equations, you sometimes have to scale both the numerator and denominator back by a constant factor to avoid an overflow error