PulseAugur
实时 12:32:06

新的采样方法使机器学习能够处理可变大小的输入

研究人员提出了一种新颖的机器学习模型框架,该框架能够处理不同大小的输入,例如点云、序列和图。该方法利用随机采样映射来比较和近似不同维度的输入,解决了泛化到更大未见数据和高效评估的挑战。该方法为跨越各种函数类(包括在序列、图和张量上定义的函数类)的泛化和草图提供了明确的速率。 AI

影响 能够为处理多样化和大规模数据输入的模型实现更鲁棒的泛化和高效的评估。

排序理由 该集群包含一篇详细介绍机器学习新理论框架的学术论文。

在 arXiv cs.LG 阅读 →

AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →

新的采样方法使机器学习能够处理可变大小的输入

报道来源 [2]

  1. arXiv cs.LG TIER_1 English(EN) · Eitan Levin, Venkat Chandrasekaran ·

    Any-Dimensional Learning by Sampling

    arXiv:2607.07680v1 Announce Type: cross Abstract: Many machine learning models are defined for inputs of different sizes, such as point clouds containing different numbers of points, sequences of tokens of different lengths, and graphs on different numbers of nodes. Such models a…

  2. arXiv cs.LG TIER_1 English(EN) · Venkat Chandrasekaran ·

    Any-Dimensional Learning by Sampling

    Many machine learning models are defined for inputs of different sizes, such as point clouds containing different numbers of points, sequences of tokens of different lengths, and graphs on different numbers of nodes. Such models are trained on finitely-many examples of necessaril…