We need to talk about random seeds

Anonymous

Abstract: Modern neural network libraries all take as a hyperparameter a random seed, typically used to determine the initial state of the model parameters. This position piece argues that there are some safe uses for random seeds: as part of the hyperparameter search to select a good model, creating an ensemble of several models, or measuring the sensitivity of the training algorithm to the random seed hyperparameter. It argues that some uses for random seeds are risky: using a fixed random seed for ``replicability'' and varying only the random seed to create score distributions for performance comparison. An analysis of 85 recent publications from the ACL Anthology shows that more than 50% contain risky uses of random seeds.