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 [1].
Asymptotic Study of Stochastic Adaptive Algorithms in Non-convex Landscape
Authors: Sébastien Gadat, Ioana Gavra
JMLR 2022 | Venue PDF | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Theoretical | This paper studies some asymptotic properties of adaptive algorithms widely used in optimization and machine learning, and among them Adagrad and Rmsprop... We adopt the point of view of stochastic algorithms and establish the almost sure convergence of these methods when using a decreasing step-size towards the set of critical points of the target function. With a mild extra assumption on the noise, we also obtain the convergence towards the set of minimizers of the function. Along our study, we also obtain a convergence rate of the methods, in the vein of the works of Ghadimi and Lan (2013). |
| Researcher Affiliation | Academia | S ebastien Gadat EMAIL Toulouse School of Economics Universit e Toulouse I Capitole Esplanade de l Universit e, 31080 Toulouse, France Institut Universitaire de France Ioana Gavra EMAIL IRMAR, Universit e de Rennes 2 Place du recteur Henri Le Moal 35043 Rennes, France |
| Pseudocode | No | The paper describes algorithms using mathematical equations (e.g., Equation (1): 'θn+1 = θn γn+1 gn+1 wn + ε wn+1 = wn + γn+1(png 2 n+1 qnwn)'), but it does not contain a structured pseudocode block or algorithm section with numbered steps, inputs, and outputs. |
| Open Source Code | No | The paper does not provide any statement about code availability, nor does it include links to repositories or supplementary materials for source code. |
| Open Datasets | No | The paper presents a theoretical study of stochastic adaptive algorithms and does not involve experiments on specific datasets. |
| Dataset Splits | No | The paper is theoretical and does not involve experiments requiring dataset splits. |
| Hardware Specification | No | The paper is a theoretical study and does not describe any experimental hardware. |
| Software Dependencies | No | The paper is a theoretical study and does not describe any specific software dependencies with version numbers. |
| Experiment Setup | No | The paper is a theoretical study and does not provide details on experimental setup, hyperparameters, or training configurations. |