arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2406.01149stat.MLcs.AIcs.ITcs.LGmath.IT
收藏

混合线性回归的不可知学习:基于EM和AM算法

Agnostic Learning of Mixed Linear Regressions with EM and AM Algorithms

Indian Institute of Technology, Bombay(印度理工学院孟买分校);Halıcıoğlu Data Science Institute, University of California, San Diego(加州大学圣地亚哥分校哈利乔格鲁数据科学学院)

Avishek Ghosh, Arya Mazumdar

AI总结:

本文研究了在无生成模型假设下混合线性回归的不可知学习问题,证明了在可分性和良好初始化条件下,EM和AM算法能收敛到总体损失最小化器,实现不可知学习。

摘要:

混合线性回归是参数统计学和机器学习中一个被充分研究的问题。给定一组样本,即协变量和标签的元组,混合线性回归的任务是找到一小组最能拟合这些样本的线性关系。通常假设标签是随机选择两个或多个线性函数之一,将该选定函数应用于协变量,并可能向结果中引入噪声来随机生成的。在这种情况下,目标是在一定的参数误差范围内估计真实的线性函数。此前已有研究分析了流行的期望最大化(EM)和交替最小化(AM)算法在此问题上的应用。在本文中,我们考虑了在没有此类生成模型的情况下,从样本中进行混合线性回归不可知学习的更一般问题。具体而言,我们证明了在可分性和良好初始化的标准条件下,AM和EM算法通过收敛到总体损失最小化器(针对适当定义的损失函数),实现了混合线性回归中的不可知学习。在某种意义上,这表明了AM和EM算法的强大之处,即使在没有可实现的生成模型的情况下,它们也能收敛到“最优解”。

英文摘要:

Mixed linear regression is a well-studied problem in parametric statistics and machine learning. Given a set of samples, tuples of covariates and labels, the task of mixed linear regression is to find a small list of linear relationships that best fit the samples. Usually it is assumed that the label is generated stochastically by randomly selecting one of two or more linear functions, applying this chosen function to the covariates, and potentially introducing noise to the result. In that situation, the objective is to estimate the ground-truth linear functions up to some parameter error. The popular expectation maximization (EM) and alternating minimization (AM) algorithms have been previously analyzed for this. In this paper, we consider the more general problem of agnostic learning of mixed linear regression from samples, without such generative models. In particular, we show that the AM and EM algorithms, under standard conditions of separability and good initialization, lead to agnostic learning in mixed linear regression by converging to the population loss minimizers, for suitably defined loss functions. In some sense, this shows the strength of AM and EM algorithms that converges to ``optimal solutions'' even in the absence of realizable generative models.

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。

↑