Reproducible AI Requires Reproducible Randomness· 可复现 AI 需要可复现的随机性
Pseudorandom number generators (PRNGs) constitute indispensable computational tools across multiple scientific domains, including Monte Carlo simulations, stochastic computing, and artificial intelligence (AI). The reproducibility of such applications critically depends on the ability of PRNG implementations to generate identical sequences across software environments when initialized from the same internal state. These algorithms enable the simulation of stochastic processes while providing deterministic and repeatable behaviour, thereby facilitating reproducible experiments. Modern PRNG implementations may be initialized through either a seed or, more accurately, an initial state that exceeds the capacity of a conventional integer seed. However, reliance on a simple seed alone frequently
探讨了可复现随机性在 AI 中的重要性及实现方法。
- 核心方法
- 提出使用更复杂的初始状态而非单一随机种子来初始化伪随机数生成器，以增强跨环境的复现能力。
- 适合谁读
- 研究者
- 要解决的问题
- 现代 AI 应用中，仅依赖简单的随机种子难以保证跨平台和跨环境的实验结果复现性。
- 关键实验
- 未提供
- 主要贡献
- 强调了可复现的随机性对于 AI 实验的重要性，并提供了实现这一目标的具体方法。
- 意义与局限
- 促进 AI 研究的可复现性，提高研究透明度和可信度，但可能增加实验设置的复杂性。