5 papers
Why Smaller Is Slower? Dimensional Misalignment in Compressed LLMs
Jihao Xin, Tian Lyu, Qilong Pan +2
Post-training compression reduces LLM parameter counts but often produces irregular tensor dimensions that degrade GPU performance -- a phenomenon we call \emph{dimensional misalig…
Modeling High-Resolution Spatio-Temporal Wind with Deep Echo State Networks and Stochastic Partial Differential Equations
Kesen Wang, Minwoo Kim, Stefano Castruccio +1
In the past decades, clean and renewable energy has gained increasing attention due to a global effort on carbon footprint reduction. In particular, Saudi Arabia is gradually shift…
A Generalized Unified Skew-Normal Process with Neural Bayes Inference
Kesen Wang, Marc G. Genton
In recent decades, statisticians have been increasingly encountering spatial data that exhibit non-Gaussian behaviors such as asymmetry and heavy-tailedness. As a result, the assum…
Multivariate Unified Skew-t Distributions And Their Properties
Kesen Wang, Maicon J. Karling, Reinaldo B. Arellano-Valle +1
The unified skew-t (SUT) is a flexible parametric multivariate distribution that accounts for skewness and heavy tails in the data. A few of its properties can be found scattered i…
Which Parameterization of the Matérn Covariance Function?
Kesen Wang, Sameh Abdulah, Ying Sun +1
The Matérn family of covariance functions is currently the most popularly used model in spatial statistics, geostatistics, and machine learning to specify the correlation between t…