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..
Stability and Sharper Risk Bounds with Convergence Rate $\tilde{O}(1/n^2)$
Authors: Bowei Zhu, Shaojie Li, Mingyang Yi, Yong Liu
NeurIPS 2025 | Venue PDF | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Theoretical | This paper focuses on learning theory. This paper focuses on learning theory and does not include experiments. This paper focuses on learning theory and does not include experiments. This paper focuses on learning theory and does not include experiments. This paper focuses on learning theory and does not include experiments. This paper focuses on learning theory and does not include experiments. This paper focuses on learning theory and does not include experiments. |
| Researcher Affiliation | Academia | Bowei Zhu1,2,3, Shaojie Li1,2,3, , Mingyang Yi1, , Yong Liu1,2,3, 1Gaoling School of Artificial Intelligence, Renmin University of China, Beijing, China 2Beijing Key Laboratory of Research on Large Models and Intelligent Governance 3Engineering Research Center of Next-Generation Intelligent Search and Recommendation, MOE EMAIL |
| Pseudocode | No | The paper describes the procedures for PGD and SGD in text paragraphs (e.g., 'Here we introduce the procedure of the PGD algorithm.' and 'Here we introduce the procedure of the standard SGD algorithm.'), but does not present them as structured pseudocode blocks or algorithms. |
| Open Source Code | No | This paper focuses on learning theory and does not include experiments. The paper does not release new assets. |
| Open Datasets | No | This paper focuses on learning theory and does not include experiments. The paper discusses theoretical concepts using abstract 'training data independent and identically distributed (i.i.d.) observations S = {z1, . . . , zn}' but does not refer to any specific named or publicly available dataset. |
| Dataset Splits | No | This paper focuses on learning theory and does not include experiments. Since no specific datasets are mentioned or utilized in experiments, there are no dataset splits provided. |
| Hardware Specification | No | This paper focuses on learning theory and does not include experiments. |
| Software Dependencies | No | This paper focuses on learning theory and does not include experiments. |
| Experiment Setup | No | This paper focuses on learning theory and does not include experiments. |