研究人员开发了一种新的方法，可以在不通过模型运行样本的情况下估计宽的、随机初始化的多层感知器（MLP）的预期输出。这种“机制估计”方法利用了累积量和Hermite展开等工具，与传统的蒙特卡洛采样相比，可以提供更准确的结果，尤其适用于宽网络。该技术也更有效，所需的浮点运算（FLOPs）更少，并且在估计罕见事件和用于模型训练方面显示出特别的潜力，有可能降低灾难性的尾部风险。 AI
影响 提供了一种更有效、可能更安全的方法来训练模型，尤其是在减轻罕见但影响重大的风险方面。
排序理由 这是一篇研究论文，详细介绍了一种用于估计MLP输出的新理论和经验方法。
AI 生成摘要 · Google Gemini · 来自 4 个来源。 我们如何撰写摘要 →
<p><em>This post covers joint work with Wilson Wu, George Robinson, Mike Winer, Victor Lecomte and Paul Christiano. Thanks to Geoffrey Irving and Jess Riedel for comments on the post.</em></p> <p>In ARC's latest paper, we study the following problem: given a randomly initialized …
arXiv:2605.05179v1 Announce Type: new Abstract: By far the most common way to estimate an expected loss in machine learning is to draw samples, compute the loss on each one, and take the empirical average. However, sampling is not necessarily optimal. Given an MLP at initializati…
<p><em>This post covers joint work with Wilson Wu, George Robinson, Mike Winer, Victor Lecomte and Paul Christiano. Thanks to Geoffrey Irving and Jess Riedel for comments on the post.</em></p> <p>In ARC's latest paper, we study the following problem: given a randomly initialized …
By far the most common way to estimate an expected loss in machine learning is to draw samples, compute the loss on each one, and take the empirical average. However, sampling is not necessarily optimal. Given an MLP at initialization, we show how to estimate its expected output …