Lottery Ticket Hypothesis

The Lottery Ticket Hypothesis claims that neural networks used in machine learning get most of their performance from sub-networks that are already present at initialization that approximate the final policy ("lotterywinning tickets"). The training process would, under this model, work by increasing weight on the lottery ticket sub-network and reducing weight on the rest of the network.

The hypothesis was proposed in a paper by Jonathan Frankle and Micheal Carbin of MIT CSAIL.

The Lottery Ticket Hypothesis claims that neural networks used in machine learning get most of their performance from sub-networks that are already present at initialization that approximate the final policy ("lottery tickets"). The training process would, under this model, work by increasing weight on the lottery ticket sub-network and reducing weight on the rest of the network.

The Lottery Ticket Hypothesis claims that neural networks used in machine learning get most of their performance from sub-networks that are already present at initialization ("lottery tickets"). The training process would, under this model, work by increasing weight on the lottery ticket sub-network and reducing weight on the rest of the network.

Created by abramdemski at 3y