arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2104.03113cs.LGcs.MA
收藏

棋盘游戏的标度缩放定律

Scaling Scaling Laws with Board Games

Andy L. Jones

摘要:

目前,机器学习领域最大规模的实验所需的资源远远超出了除少数机构外的所有机构的预算。幸运的是,最近的研究表明,这些大型实验的结果往往可以从一系列小得多、便宜得多的实验的结果中推断出来。在这项工作中,我们表明,不仅可以根据模型的大小进行外推,但问题的大小也是如此。通过使用AlphaZero和Hex进行一系列实验,我们表明,随着游戏变得越来越大,越来越难,固定计算量所能达到的性能会可预测地下降。随着我们的主要结果,我们进一步表明,测试时间和训练时间计算可用于代理可以权衡,同时保持性能。

英文摘要:

The largest experiments in machine learning now require resources far beyond the budget of all but a few institutions. Fortunately, it has recently been shown that the results of these huge experiments can often be extrapolated from the results of a sequence of far smaller, cheaper experiments. In this work, we show that not only can the extrapolation be done based on the size of the model, but on the size of the problem as well. By conducting a sequence of experiments using AlphaZero and Hex, we show that the performance achievable with a fixed amount of compute degrades predictably as the game gets larger and harder. Along with our main result, we further show that the test-time and train-time compute available to an agent can be traded off while maintaining performance.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑