On the number of variables to use in principal component regression

Authors: Ji Xu, Daniel J. Hsu

NeurIPS 2019 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Theoretical We give an average-case analysis of the out-of-sample prediction error as p, n, N ! 1 with p/N ! and n/N ! β, for some constants 2 [0, 1] and β 2 (0, 1). In this average-case setting, the prediction error exhibits a double descent shape as a function of p. We also establish conditions under which the minimum risk is achieved in the interpolating (p > n) regime. The proofs of the results are detailed in the full version of the paper [19].
Researcher Affiliation Academia Ji Xu Columbia University jixu@cs.columbia.edu Daniel Hsu Columbia University djhsu@cs.columbia.edu
Pseudocode No The paper does not contain any pseudocode or algorithm blocks.
Open Source Code No The paper does not provide any statements about open-source code availability or links to repositories.
Open Datasets No The paper uses a synthetic data model ('Our data (x1, y1), . . . , (xn, yn) are assumed to be i.i.d. with xi N(0, )') for theoretical analysis and does not mention or provide access to any public datasets.
Dataset Splits No The paper is theoretical and analyzes a synthetic data model. It does not describe any specific training, validation, or test dataset splits for empirical reproduction.
Hardware Specification No The paper is theoretical and does not mention any specific hardware used for experiments.
Software Dependencies No The paper does not provide any specific software dependencies with version numbers.
Experiment Setup No The paper is theoretical and does not describe an empirical experimental setup with hyperparameters or system-level training settings.