|
|
|
|
|
|
by in-silico
9 hours ago
|
|
|
This algorithm: sample a bunch of latents, train the model using the one with the lowest error. IWAE: sample a bunch of latents, weight the loss of training the model using each one by softmax(-error). For images and text where the errors have large variance, those weights become one-hot, yielding this algorithm. |
|
|