How to reproduce results from the paper? about tcn HOT 4 CLOSED

Regarding your questions:

1. It's mainly a problem of training instability, 2.8e-5 and 4.2e-5 are already below what I reported. Note that these are MSE errors and random guess gives you only ~0.17.

2. Not sure what exactly your design is, but multivariate TCN has already been widely applied and I think it'd be (generally) a good direction to pursue.

from tcn.

Hi @johnsyin ,

Thanks for your interest in our work!

In our paper, I took the average of the test set results from the last 3 epochs. In your case, I think you can also do the same. An alternative way is to use annealing learning rate; after the learning rate is annealed to the bottom, the test result will also converge (whose result you can then report).

But given the numbers you provided, I think you have already reproduced the results :-)

from tcn.

Hi Jerry,

Loved your paper, very appreciate you open sourced the work! I am a MS student researching this method.

1. The last 3 numbers I provided has a mean of 1e-4, why is it considered as result reproduced (5.8e-5)?
2. If I can have your advice, do you think multivariate TCN with Squeeze-and-excitation weighted temporal block will work?

from tcn.

Thank you for your reply!

from tcn.