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.
Functional Gradient Boosting based on Residual Network Perception
Authors: Atsushi Nitanda, Taiji Suzuki
ICML 2018 | Venue PDF | LLM Run Details | Input Tokens: 18,763 Total number of tokens sent to the LLM as input for this paper's analysis. | Output Tokens: 3,048 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 | Experimental results show superior performance of the proposed method over state-of-the-art methods such as Light GBM. |
| Researcher Affiliation | Academia | 1Graduate School of Information Science and Technology, The University of Tokyo 2Center for Advanced Intelligence Project, RIKEN. |
| Pseudocode | Yes | Algorithm 1 Res FGB [...] Algorithm 2 Sample-splitting Res FGB |
| Open Source Code | No | The paper does not provide any statement or link indicating that the source code for the described methodology is publicly available. |
| Open Datasets | Yes | We use the following benchmark datasets: letter, usps, ijcnn1, mnist, covtype, and susy. |
| Dataset Splits | Yes | For datasets not providing a fixed test set, we first divide each dataset randomly into two parts: 80% for training and the rest for test. We next divide each training set randomly and use 80% for training and the rest for validation. |
| Hardware Specification | No | The paper does not provide specific details about the hardware used for experiments. |
| Software Dependencies | No | The paper mentions using a |
| Experiment Setup | Yes | The number of hidden units in each layer is set to 100 or 1000. Linear classifiers and embeddings are trained by Nesterov s momentum method. The learning rate is chosen from {10 3, 10 2, 10 1, 1}. These parameters and the number of iterations T are tuned based on the performance on the validation set. |