Research project investigating whether training-only context sparsity can predict the marginal held-out benefit of increasing n-gram order.
-
Updated
Aug 17, 2026 - Python
Research project investigating whether training-only context sparsity can predict the marginal held-out benefit of increasing n-gram order.
Code for the EUSIPCO 2025 paper "Impact of Data Sparsity on Machine Learning for Fault Detection in Power System Protection". Quantifies how relay and bus failures, downsampling, missing voltage/current channels and communication dropouts degrade fault detection and fault line identification.
Bachelor Thesis “Information-Theoretic Champion Abstraction for Mitigating Data Sparsity in League of Legends” by Panagiotis Theologou, Department of Informatics and Telematics, Harokopio University, Athens, 2026.
To associate your repository with the data-sparsity topic, visit your repo's landing page and select "manage topics."