Large Learning Rate Tames Homogeneity: Convergence and Balancing Effect

Authors: Yuqing Wang, Minshuo Chen, Tuo Zhao, Molei Tao

ICLR 2022 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Numerical experiments are provided to support our theory.
Researcher Affiliation Academia Yuqing Wang, Minshuo Chen, Tuo Zhao, Molei Tao Georgia Institute of Technology {ywang3398,mchen393,tourzhao,mtao}@gatech.edu
Pseudocode No The paper describes mathematical update rules for Gradient Descent but does not include structured pseudocode or algorithm blocks.
Open Source Code No The paper does not provide any statement or link indicating the availability of open-source code for the described methodology.
Open Datasets No The paper describes generating elements for matrix A from a Gaussian distribution and generating initial conditions (X0, Y0) randomly. It does not mention using any publicly available or open datasets with concrete access information.
Dataset Splits No The paper does not provide specific details about training, validation, or test dataset splits.
Hardware Specification No The paper does not explicitly describe the hardware used to run its experiments, such as specific GPU or CPU models.
Software Dependencies No The paper mentions Gradient Descent (GD) but does not provide specific software dependencies with version numbers (e.g., programming languages, libraries, or frameworks).
Experiment Setup Yes The initial conditions are randomly generated, respectively with ( x0 , y0 ) = (9, 1), ( x0 , y0 ) = (19, 1), and ( x0 , y0 ) = (99, 1); the learning rates are chosen within the range of Theorem 3.1 from large to small as h0, 6 7h0 for the 1st-6th columns respectively where h0 = 4/( x0 2 + y0 2 + 8).