Stability and Generalization for Randomized Coordinate Descent

Authors: Puyu Wang, Liang Wu, Yunwen Lei

IJCAI 2021 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental We report experimental results in Section 6 and present some proofs in Section 7. Our analysis shows that RCD enjoys better stability as compared to stochastic gradient descent.
Researcher Affiliation Academia 1School of Mathematics, Northwest University, Xi an 710127, China 2Center of Statistical Research, School of Statistics, Southwestern University of Finance and Economics, Chengdu 611130, China 3School of Computer Science, University of Birmingham, Birmingham B15 2TT, UK
Pseudocode No The paper describes the RCD update rule (Equation 2) but does not provide structured pseudocode or an algorithm block.
Open Source Code No The paper does not provide any statement about releasing source code or a link to a code repository.
Open Datasets Yes We consider the least square regression for two datasets: ionosphere, svmguide3 and MNIST.
Dataset Splits No We follow the set up in Hardt et al. [2016], i.e., we consider two neighboring datasets and run RCD/SGD with ηt 0.01 on these neighboring datasets to produce two iterate sequences {wt}, {w t}. We then plot the Euclidean distance between two iterate sequences as a function of the iteration number. We consider the least square regression for two datasets: ionosphere, svmguide3 and MNIST.
Hardware Specification No The paper does not provide any specific hardware details (e.g., GPU/CPU models, memory) used for running its experiments.
Software Dependencies No The paper does not provide specific ancillary software details with version numbers.
Experiment Setup Yes We follow the set up in Hardt et al. [2016], i.e., we consider two neighboring datasets and run RCD/SGD with ηt 0.01 on these neighboring datasets to produce two iterate sequences {wt}, {w t}. We repeat the experiments 100 times and report the average of results.