Non-asymptotic Optimal Prediction Error for Growing-dimensional Partially Functional Linear Models
This work addresses theoretical guarantees for prediction in high-dimensional functional data models, which is incremental as it extends existing asymptotic results to non-asymptotic settings.
The paper tackles the prediction error bounds for partially functional linear models with growing dimensions, establishing non-asymptotic rate-optimal upper and lower bounds and showing prediction consistency when the number of multivariate covariates increases with sample size, with findings implying a trade-off between non-functional predictors and kernel principal components.
Under the reproducing kernel Hilbert spaces (RKHS), we consider the penalized least-squares of the partially functional linear models (PFLM), whose predictor contains both functional and traditional multivariate parts, and the multivariate part allows a divergent number of parameters. From the non-asymptotic point of view, we focus on the rate-optimal upper and lower bounds of the prediction error. An exact upper bound for the excess prediction risk is shown in a non-asymptotic form under a more general assumption known as the effective dimension to the model, by which we also show the prediction consistency when the number of multivariate covariates $p$ slightly increases with the sample size $n$. Our new finding implies a trade-off between the number of non-functional predictors and the effective dimension of the kernel principal components to ensure prediction consistency in the increasing-dimensional setting. The analysis in our proof hinges on the spectral condition of the sandwich operator of the covariance operator and the reproducing kernel, and on sub-Gaussian and Berstein concentration inequalities for the random elements in Hilbert space. Finally, we derive the non-asymptotic minimax lower bound under the regularity assumption of the Kullback-Leibler divergence of the models.