An_idi0t

Thanks for replying,really convincing. You update the parameters using meta-train, and use this updated parameters to get loss on meta-test, and sum up.When tasks are mutually exclusive, why this policy...

do anyone give some explanations? really confused，yayayayayay

0.4

follow了一下，所以您是将当前观测到的样本当作是从do(x)之后的distribution中采样来的，因此给他们赋予了一个$weight = 1/P(x|M=m)$对吧？那为什么P(x|M=m) 可以近似为 L2-norm呢？这是基于什么得出的呢？