High Dimensional
High-dimensional data analysis focuses on extracting meaningful information and building predictive models from datasets with numerous variables, often exceeding the number of observations. Current research emphasizes developing computationally efficient algorithms, such as stochastic gradient descent and its variants, and novel model architectures like graph neural networks and deep learning approaches tailored to handle the unique challenges posed by high dimensionality, including issues of sparsity and missing data. These advancements are crucial for addressing complex problems across diverse fields, including scientific modeling, robotics, and financial risk assessment, where high-dimensional data are increasingly prevalent.
Papers
Interpretation of High-Dimensional Regression Coefficients by Comparison with Linearized Compressing Features
Joachim Schaeffer, Jinwook Rhyu, Robin Droop, Rolf Findeisen, Richard Braatz
Equivariant spatio-hemispherical networks for diffusion MRI deconvolution
Axel Elaldi, Guido Gerig, Neel Dey
Efficient Sample-optimal Learning of Gaussian Tree Models via Sample-optimal Testing of Gaussian Mutual Information
Sutanu Gayen, Sanket Kale, Sayantan Sen
Accelerating spherical K-means clustering for large-scale sparse document data
Kazuo Aoyama, Kazumi Saito