Notice: This website is continuously updated as new conference proceedings and journal volumes are published. Consequently, the figures presented here may differ from those reported in our publications.
A brief overview of our methodology is provided on the Methods page, along with references to publications documenting our approach and links to the code and data used in each study.
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.
Shadowing Properties of Optimization Algorithms
Authors: Antonio Orvieto, Aurelien Lucchi
NeurIPS 2019 | Venue PDF | LLM Run Details | Input Tokens: 18,429 Total number of tokens sent to the LLM as input for this paper's analysis. | Output Tokens: 5,463 Total number of tokens produced by the LLM (including reasoning/thinking tokens) for this paper's analysis.
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | We back-up and complement our theory with experiments on machine learning problems. |
| Researcher Affiliation | Academia | Antonio Orvieto Department of Computer Science ETH Zurich, Switzerland Aurelien Lucchi Department of Computer Science ETH Zurich, Switzerland |
| Pseudocode | No | The paper describes algorithms using mathematical equations but does not provide structured pseudocode or algorithm blocks. |
| Open Source Code | No | The paper does not provide any explicit statements about releasing source code or links to a code repository for the described methodology. |
| Open Datasets | Yes | We consider the problem of binary classification of digits 3 and 5 from the MNIST data-set [33]. |
| Dataset Splits | No | The paper mentions 'n = 10000 training examples' but does not provide specific percentages or counts for training, validation, or test splits. It implicitly evaluates on the remaining data, but no explicit split details are provided. |
| Hardware Specification | No | The paper does not provide specific details about the hardware (e.g., CPU, GPU models, memory) used for running the experiments. |
| Software Dependencies | No | The paper mentions 'fourth-order Runge-Kutta' as a simulation method, but does not specify any software libraries or dependencies with version numbers. |
| Experiment Setup | Yes | We simulate GD-ODE using fourth-order Runge-Kutta[21] (high-accuracy integration) and run GD with learning rate h = 1. We simulate HB-ODE and run HB under the same conditions, using = 0.3 (to induce a significant momentum). |