Fine-Grained Analysis of Stability and Generalization for Stochastic Gradient Descent

Authors: Yunwen Lei, Yiming Ying

ICML 2020 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Theoretical In this paper, we provide a fine-grained analysis of stability and generalization for SGD by substantially relaxing these assumptions. Firstly, we establish stability and generalization for SGD by removing the existing bounded gradient assumptions.
Researcher Affiliation Academia Yunwen Lei 1 2 Yiming Ying 3 1Department of Computer Science, University of Kaiserslautern, Germany 2School of Computer Science, University of Birmingham, United Kingdom 3Department of Mathematics and Statistics, State University of New York at Albany, USA.
Pseudocode No The paper describes the SGD update rule mathematically (Definition 2) but does not provide a structured pseudocode or algorithm block.
Open Source Code No The paper does not provide any statement about releasing open-source code or a link to a code repository.
Open Datasets No The paper discusses 'training examples' theoretically but does not reference or provide access information for any specific, publicly available dataset.
Dataset Splits No The paper is theoretical and does not perform experiments with specific datasets, therefore no dataset split information is provided.
Hardware Specification No The paper is theoretical and does not report on experiments, therefore no hardware specifications are mentioned.
Software Dependencies No The paper is theoretical and does not report on experiments, therefore no software dependencies with version numbers are listed.
Experiment Setup No The paper is theoretical and does not describe experiments, therefore no experimental setup details are provided.