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.
Optimal Algorithms for Online Convex Optimization with Adversarial Constraints
Authors: Abhishek Sinha, Rahul Vaze
NeurIPS 2024 | Venue PDF | LLM Run Details | Input Tokens: 29,122 Total number of tokens sent to the LLM as input for this paper's analysis. | Output Tokens: 4,747 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 | In Section 4, we evaluate the practical performance of our algorithm in the online credit card fraud detection problem with a highly imbalanced dataset. |
| Researcher Affiliation | Academia | School of Technology and Computer Science Tata Institute of Fundamental Research Mumbai 400005, India |
| Pseudocode | Yes | Algorithm 1 Online Policy for COCO |
| Open Source Code | Yes | The code has been publicly released [Sinha, 2024b]. |
| Open Datasets | Yes | We experiment with a publicly available credit card transaction dataset [Dal Pozzolo et al., 2014]. |
| Dataset Splits | No | The paper states it learns 'in an entirely online fashion starting from random initialization' and does not specify traditional train/validation/test splits. |
| Hardware Specification | Yes | The network is then trained using Algorithm 1 on a quad-core CPU with 8 GB RAM. |
| Software Dependencies | No | The paper mentions training a neural network but does not specify any software dependencies with version numbers. |
| Experiment Setup | Yes | We choose a simple network architecture with a single hidden layer containing H = 10 hidden nodes and sigmoid nonlinearities. Initially, all weights are independently sampled from a standard normal distribution. By varying the hyperparameter λ, we obtain the ROC curve shown in Figure 1. |