When the stakes are high, a greater level of quality and reliability is required. Such as the case with the gaming industry, as high rollers take their chances at winning jackpot. However, no one would want to take their chances with a poor quality ticket that will not weather the many hazards that comes with being handled in adverse conditions.
Similar to entertainment ticketing, lottery tickets and betting slips need to be of a certain quality to be ensured, even in adverse conditions.
– Sequential numbering
– Smooth surface
– Tearing lines
– Hot stamping foil
– Hologram label
– High quality, reasonable price and fast delivery
– Anti-counterfeit technology
Donate to arXiv
Please join the Simons Foundation and our generous member organizations in supporting arXiv during our giving campaign September 23-27. 100% of your contribution will fund improvements and new initiatives to benefit arXiv’s global scientific community.
[secure site, no need to create account]
Computer Science > Machine Learning
Title: The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks
Donate to arXiv Please join the Simons Foundation and our generous member organizations in supporting arXiv during our giving campaign September 23-27. 100% of your contribution will fund ]]>
Abstract: Neural network pruning techniques can reduce the parameter counts of trained networks by over 90%, decreasing storage requirements and improving computational performance of inference without compromising accuracy. However, contemporary experience is that the sparse architectures produced by pruning are difficult to train from the start, which would similarly improve training performance.
We find that a standard pruning technique naturally uncovers subnetworks whose initializations made them capable of training effectively. Based on these results, we articulate the “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.
We present an algorithm to identify winning tickets and a series of experiments that support the lottery ticket hypothesis and the importance of these fortuitous initializations. We consistently find winning tickets that are less than 10-20% of the size of several fully-connected and convolutional feed-forward architectures for MNIST and CIFAR10. Above this size, the winning tickets that we find learn faster than the original network and reach higher test accuracy.