Notice: The reproducibility variables underlying each score are classified using an automated LLM-based pipeline, validated against a manually labeled dataset. LLM-based classification introduces uncertainty and potential bias; scores should be interpreted as estimates. Full accuracy metrics and methodology are described in Coakley et alK. L. Coakley, T. Snelleman, H. Hoos, and O. E. Gundersen, "The embrace of open science: An analysis of a decade of AI research and 56 800 conference papers," Under Review, 2026..

Statistical Guarantees for High-Dimensional Stochastic Gradient Descent

Authors: Jiaqi Li, Zhipeng Lou, Johannes Schmidt-Hieber, Wei Biao Wu

NeurIPS 2025 | Venue PDF | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Theoretical This paper contributes to theoretical advancements for understanding constant learning-rate SGD and its averaged variant (ASGD) in the challenging high-dimensional regime.
Researcher Affiliation Academia Jiaqi Li Department of Statistics University of Chicago Chicago, IL 60637 EMAIL Zhipeng Lou Department of Mathematics University of California, San Diego La Jolla, CA 92093 EMAIL Johannes Schmidt-Hieber Department of Applied Mathematics University of Twente Enschede, Netherlands EMAIL Wei Biao Wu Department of Statistics University of Chicago Chicago, IL 60637 EMAIL
Pseudocode No The paper describes algorithms like SGD and ASGD using mathematical equations (e.g., Eq. 2 and 3) and textual descriptions, but does not present them in structured pseudocode or an algorithm block format.
Open Source Code No This paper contributes to theoretical guarantees of high-dimensional SGD. This paper does not include experiments requiring code.
Open Datasets No This paper contributes to theoretical guarantees of high-dimensional SGD. This paper does not include experiments requiring code.
Dataset Splits No This paper contributes to theoretical guarantees of high-dimensional SGD. This paper does not include experiments requiring code.
Hardware Specification No This paper contributes to theoretical guarantees of high-dimensional SGD. This paper does not include experiments requiring code.
Software Dependencies No This paper contributes to theoretical guarantees of high-dimensional SGD. This paper does not include experiments requiring code.
Experiment Setup No This paper does not include experiments, therefore, no experimental setup details are provided.