论文标题
用于分类的功能混合物
Functional mixture-of-experts for classification
论文作者
论文摘要
我们开发出一种混合物（ME）方法，以进行多类分类，其中预测因子是单变量函数。它由一个ME模型组成，在该模型中，门控网络和专家网络都是在具有功能输入的多项式logistic激活函数上构建的。我们执行正规化的最大似然估计，其中系数函数在靶向导数上享有可解释的稀疏性约束。我们开发了像EM-LASSO这样的算法来计算正则化MLE并评估模拟和真实数据的建议方法。
We develop a mixtures-of-experts (ME) approach to the multiclass classification where the predictors are univariate functions. It consists of a ME model in which both the gating network and the experts network are constructed upon multinomial logistic activation functions with functional inputs. We perform a regularized maximum likelihood estimation in which the coefficient functions enjoy interpretable sparsity constraints on targeted derivatives. We develop an EM-Lasso like algorithm to compute the regularized MLE and evaluate the proposed approach on simulated and real data.
