Search Results for author:
Found 7 papers, 0 papers with code
Statistical and computational rates in high rank tensor estimation
We find that high-dimensional latent variable tensors are of log-rank; the fact explains the pervasiveness of low-rank tensors in applications.
Sufficient dimension reduction for feature matrices
We address the problem of sufficient dimension reduction for feature matrices, which arises often in sensor network localization, brain neuroimaging, and electroencephalography analysis.
Smooth tensor estimation with unknown permutations
A phase transition phenomenon is revealed with respect to the smoothness threshold needed for optimal recovery.
Nonparametric Trace Regression in High Dimensions via Sign Series Representation
Trace regression is a widely used method to model effects of matrix predictors and has shown great success in matrix learning.
Beyond the Signs: Nonparametric Tensor Completion via Sign Series
A nonparametric approach to tensor completion is developed based on a new model which we coin as sign representable tensors.
Tensor denoising and completion based on ordinal observations
Higher-order tensors arise frequently in applications such as neuroimaging, recommendation system, social network analysis, and psychological studies.
Supervised tensor decomposition with features on multiple modes
Here, we develop a tensor decomposition method that incorporates multiple feature matrices as side information.
