arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2409.01413math.OCcs.LG
收藏

面向稀疏学习的概率迭代硬阈值方法

Probabilistic Iterative Hard Thresholding for Sparse Learning

Matteo Bergamaschi, Andrea Cristofari, Vyacheslav Kungurtsev, Francesco Rinaldi

AI总结:

针对高维小样本统计建模及大数据下带噪梯度的稀疏优化方法收敛性不足问题,提出带基数约束的概率迭代硬阈值方法,证明其随机过程收敛性并在两类机器学习任务中验证性能。

摘要:

在统计建模中,当数据维度相对于样本量处于不利状态时,挖掘真实数据中隐藏的稀疏性对构建准确的统计模型至关重要。用于统计向量中非零元素数量的“l0范数”,在被纳入优化问题以最小化给定模型对一组观测值的拟合误差时,是一种强大可靠的稀疏性强制机制。然而,在大数据场景下,出于计算必要性必须评估带噪声的梯度估计值,目前学界关于能可靠收敛的方法的研究还很少。本文提出了一种求解带基数约束的期望目标优化问题的方法,证明了其底层随机过程的收敛性,并在两个机器学习问题上验证了该方法的性能。

英文摘要:

For statistical modeling wherein the data regime is unfavorable in terms of dimensionality relative to the sample size, finding hidden sparsity in the ground truth can be critical in formulating an accurate statistical model. The so-called "l0 norm" which counts the number of non-zero components in a vector, is a strong reliable mechanism of enforcing sparsity when incorporated into an optimization problem for minimizing the fit of a given model to a set of observations. However, in big data settings wherein noisy estimates of the gradient must be evaluated out of computational necessity, the literature is scant on methods that reliably converge. In this paper we present an approach towards solving expectation objective optimization problems with cardinality constraints. We prove convergence of the underlying stochastic process, and demonstrate the performance on two Machine Learning problems.

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。

↑