论文标题
我们需要谈论随机种子
We need to talk about random seeds
论文作者
论文摘要
现代神经网络库都作为一个随机种子，通常用于确定模型参数的初始状态。这篇文章认为，随机种子有一些安全的用途：作为超参数搜索的一部分，可以选择一个好的模型，创建几种模型的合奏，或测量训练算法对随机种子超参数的敏感性。它认为随机种子的某些用途是有风险的：使用固定的随机种子来“可复制性”，并仅改变随机种子以创建得分分布以进行性能比较。对来自ACL选集的85个最新出版物的分析发现，超过50％的人包含随机种子的危险用途。
Modern neural network libraries all take as a hyperparameter a random seed, typically used to determine the initial state of the model parameters. This opinion 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 finds that more than 50% contain risky uses of random seeds.
