High-Dimensional Analysis for Generalized Nonlinear Regression: From Asymptotics to Algorithm

Authors: Jian Li, Yong Liu, Weiping Wang

AAAI 2024 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental We conduct experiments to explore the impacts of nonlinear feature mappings and subsampling, respectively. We leave the proofs and more experiments in the appendix. Our contributions can be summarized as follows: ... Finally, we validate our theoretical findings and the proposed algorithm through several experiments.
Researcher Affiliation Academia Jian Li1, Yong Liu2*, Weiping Wang1 1Institute of Information Engineering, Chinese Academy of Sciences 2Gaoling School of Artificial Intelligence, Renmin University of China
Pseudocode No The paper describes the algorithm RFRed and its optimization steps but does not include a formally structured pseudocode block or an 'Algorithm' section.
Open Source Code Yes Code: https://github.com/superlj666/Nonlinear HDA
Open Datasets Yes The training examples n = 100 are randomly drawn from the MNIST dataset (Le Cun et al. 1998).
Dataset Splits No The paper mentions 'training examples' and 'test errors' but does not provide specific details on how the dataset was split into training, validation, and test sets (e.g., percentages, sample counts, or explicit mention of a validation set).
Hardware Specification No The paper does not provide any specific details about the hardware (e.g., GPU/CPU models, memory) used for running the experiments.
Software Dependencies No Our implementation is based on Py Torch, and we fine-tune the hyperparameters through a grid search approach, exploring values for σ2 in the range of {0.01, ..., 1000} and λ {0.1, ..., 10^-5}. (Mentions PyTorch but no version).
Experiment Setup Yes We fix n = 100, S = In, m = n and change the random features dimension p [10, 400]. ... We set the same hyperparameter σ2 = 0.1. ... We fine-tune the hyperparameters through a grid search approach, exploring values for σ2 in the range of {0.01, ..., 1000} and λ {0.1, ..., 10^-5}.