Jonathan Frankle - The Lottery Ticket Hypothesis: On Sparse, Trainable Neural Networks

[@alles_anders]

When you say, it can train to full accuracy in the same number of steps - isn't that sort of untrue? If it is the same number of steps (N) to train the reduced network as the big network, wouldn't we have 2N at the end of finding and training the winning ticket?

[@EPenguin82]

Fascinating!

[@araldjean-charles3924]

For the initial conditions that work, have anybody look at how much wiggle room you have. Is there an epsilon-neighborhood of the initial state you can safely start from, and how small is epsilon?

[@jerryyuan6456]

Did you find anything on this?

[@forecastinglottery6153]

what computing power was used to achieve such results ?