Revisiting the Last-Iterate Convergence of Stochastic Gradient Methods

Authors: Zijian Liu, Zhengyuan Zhou

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

Reproducibility Variable Result LLM Response
Research Type Theoretical Ethics Statement: This is a theory work. Hence, there are no potential ethics concerns. Reproducibility Statement: We include the full proofs of all theorems in the appendix.
Researcher Affiliation Academia Zijian Liu , Zhengyuan Zhou Stern School of Business, New York University {zl3067,zzhou}@stern.nyu.edu
Pseudocode Yes Algorithm 1 Composite Stochastic Mirror Descent (CSMD) Input: x1 X, ηt > 0, t [T]. for t = 1 to T do xt+1 = argminx X h(x) + bgt, x xt + Dψ(x,xt) ηt Return x T +1
Open Source Code No No explicit statement or link providing access to the source code for the methodology described in this paper is found.
Open Datasets No The paper is theoretical and does not involve empirical evaluation on datasets.
Dataset Splits No The paper is theoretical and does not involve dataset splits for validation.
Hardware Specification No The paper is theoretical and does not describe experimental hardware specifications.
Software Dependencies No The paper is theoretical and does not mention software dependencies with specific version numbers.
Experiment Setup No The paper is theoretical and does not describe an experimental setup with specific hyperparameters or training configurations.