"lottery ticket hypothesis:" dense, randomly-initialized, feed-forward networks contain subnetworks ("winning tickets") that - when trained in isolation - reach test accuracy comparable to the original network in a similar number of iterations. The winning tickets we find have won the initialization lottery: their connections have initial weights that make training particularly effective.
有点像deepseek的专家模型
#3 Re: 诶，这个巧妙，他这个巧妙(lottery ticket hypothesis)
发表于 ： 2025年 3月 30日 13:34
由 huangchong
ɓuoɥɔɓuɐnɥ 写了： 2025年 3月 30日 13:03
"lottery ticket hypothesis:" dense, randomly-initialized, feed-forward networks contain subnetworks ("winning tickets") that - when trained in isolation - reach test accuracy comparable to the original network in a similar number of iterations. The winning tickets we find have won the initialization lottery: their connections have initial weights that make training particularly effective.