7 papers
Energy-Conscious LLM Decoding: Impact of Text Generation Strategies on GPU Energy Consumption
Alireza Nik, Michael A. Riegler, PÃ¥l Halvorsen
Decoding strategies significantly influence the quality and diversity of the generated text in Large Language Models (LLMs), yet their impact on computational resources, particular…
Principal Components for Neural Network Initialization
Nhan Phan, Thu Nguyen, Uyen Dang +2
Principal Component Analysis (PCA) is a commonly used tool for dimension reduction and denoising. Therefore, it is also widely used on the data prior to training a neural network.…
Imputation using training labels and classification via label imputation
Thu Nguyen, Tuan L. Vo, PÃ¥l Halvorsen +1
Missing data is a common problem in practical data science settings. Various imputation methods have been developed to deal with missing data. However, even though the labels are a…
Explainability of Machine Learning Models under Missing Data
Tuan L. Vo, Thu Nguyen, Luis M. Lopez-Ramos +3
Missing data is a prevalent issue that can significantly impair model performance and explainability. This paper briefly summarizes the development of the field of missing data wit…
DPERC: Direct Parameter Estimation for Mixed Data
Tuan L. Vo, Quan Huu Do, Uyen Dang +4
The covariance matrix is a foundation in numerous statistical and machine-learning applications such as Principle Component Analysis, Correlation Heatmap, etc. However, missing val…
Missing data imputation for noisy time-series data and applications in healthcare
Lien P. Le, Xuan-Hien Nguyen Thi, Thu Nguyen +3
Healthcare time series data is vital for monitoring patient activity but often contains noise and missing values due to various reasons such as sensor errors or data interruptions.…