组合模型下线性系统的学习理论
A Learning Theory in Linear Systems under Compositional Models
摘要:
我们提出了一个学习理论的线性系统运营商的培训有一个输入组成变量,并提出了贝叶斯反演方法推断未知变量从一个嘈杂的线性系统的输出。我们假设我们对算子有部分甚至没有知识,但有输入和输出的训练数据。组成变量满足变量的元素都是非负的并且总和为1的约束。我们量化了训练算子的不确定性,并以显式形式给出了随机组合模型下几种有趣情况下的训练收敛率。训练的线性算子与协方差阵,估计从地面实况输入和噪声输出数据对的训练集,进一步用于评估解决方案的后验不确定性。这种后验不确定性清楚地表明了来自噪声训练数据的不确定性传播,并解决了最终解决方案中真实算子和估计算子之间可能存在的不匹配。
英文摘要:
We present a learning theory for the training of a linear system operator having an input compositional variable and propose a Bayesian inversion method for inferring the unknown variable from an output of a noisy linear system. We assume that we have partial or even no knowledge of the operator but have training data of input and ouput. A compositional variable satisfies the constraints that the elements of the variable are all non-negative and sum to unity. We quantified the uncertainty in the trained operator and present the convergence rates of training in explicit forms for several interesting cases under stochastic compositional models. The trained linear operator with the covariance matrix, estimated from the training set of pairs of ground-truth input and noisy output data, is further used in evaluation of posterior uncertainty of the solution. This posterior uncertainty clearly demonstrates uncertainty propagation from noisy training data and addresses possible mismatch between the true operator and the estimated one in the final solution.
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。