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].
An Accelerated DFO Algorithm for Finite-sum Convex Functions
Authors: Yuwen Chen, Antonio Orvieto, Aurelien Lucchi
ICML 2020 | Venue PDF | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Finally, we validate our theoretical results empirically on several tasks and datasets. |
| Researcher Affiliation | Academia | 1Computer Science Department, ETH Z urich, Switzerland. Correspondence to: Chen, Yuwen <EMAIL>, Orvieto, Antonio <EMAIL>, Lucchi, Aurelien <EMAIL>. |
| Pseudocode | Yes | The method we propose is presented as Algorithm 1 (ZOVarag), and is an adaptation of Varag (Lan et al., 2019) to the DFO setting. |
| Open Source Code | No | The paper does not provide an explicit statement or link to open-source code for the described methodology. |
| Open Datasets | Yes | We conduct experiments for both logistic regression and ridge regression with and without ℓ2 regularization on the diabete dataset (n = 442, d = 10) from sklearn and the ijcnn1 dataset (n = 49990, d = 22) from LIBSVM. |
| Dataset Splits | No | The paper mentions using the 'diabete dataset' and 'ijcnn1 dataset' but does not specify details about training, validation, or test splits (e.g., percentages, sample counts, or explicit reference to standard splits used for reproducibility). |
| Hardware Specification | No | The paper does not specify any particular hardware (e.g., GPU models, CPU types, memory) used for running the experiments. |
| Software Dependencies | No | The paper does not provide specific version numbers for any software libraries, frameworks, or environments used (e.g., Python, PyTorch, TensorFlow versions). |
| Experiment Setup | Yes | The choice of the hyperparameters chosen for each algorithm is detailed in the appendix. |