On the Target-kernel Alignment: a Unified Analysis with Kernel Complexity

Authors: Chao Wang, Xin HE, Yuwen Wang, Junhui Wang

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

Reproducibility Variable Result LLM Response
Research Type Experimental Extensive numerical experiments further support our theoretical findings. The Python code for reproducing the numerical experiments is available on Github.
Researcher Affiliation Academia Chao Wang , Xin He , Yuwen Wang , Junhui Wang School of Statistics and Management, Shanghai University of Finance and Economics Key Laboratory of Mathematical Economics (SUFE), Ministry of Education, Shanghai Chinese University of Hong Kong wang.chao@stu.sufe.edu.cn, he.xin17@mail.shufe.edu.cn wangyw@link.cuhk.edu.hk, junhuiwang@cuhk.edu.hk
Pseudocode No The paper does not contain structured pseudocode or algorithm blocks.
Open Source Code Yes The Python code for reproducing the numerical experiments is available on Github.
Open Datasets Yes We apply both TKM and KM with check loss to the wine quality dataset, which is available in the UCI Machine Learning Repository.
Dataset Splits Yes The parameters γ and r are tuned by 5-fold cross-validation.
Hardware Specification Yes All experiments were conducted on the same hardware setup: Intel i9 13900K CPU @ 2.20GHz with 128 GB memory.
Software Dependencies No The paper mentions general software like "Python code" but does not specify library names with version numbers.
Experiment Setup Yes The data generating scheme is repeated for 50 times and all the tuning parameters are tuned to the best for both methods.