Optimal Algorithms for Online Convex Optimization with Adversarial Constraints

Authors: Abhishek Sinha, Rahul Vaze

NeurIPS 2024 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

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.