Eric P. Xing

TL;DR: This paper presents an efficient method that can remove the influences of confounding factors such as age or gender to improve the across-cohort prediction accuracy of neural networks.

TL;DR: A new decentralized system Orpheus is built to support distributed training of a general class of ML models whose parameters are represented with large matrices and which outperforms several existing baseline systems on training several representative large-scale ML models.

TL;DR: A family of orthogonality-promoting regularizers is defined by encouraging the Gram matrix of the RKHS functions to be close to an identity matrix where the closeness is measured by Bregman matrix divergences, and results suggest that the closer the functions are to being orthogonal, the smaller the generalization error is.

TL;DR: This paper presents a distribution over collections of time-dependent, infinite-dimensional trees that can be used to model evolving hierarchies, and presents an efficient and scalable algorithm for performing approximate inference in such a model.

TL;DR: A new method, called group sparse additive models (GroupSpAM), which can handle group sparsity in additive models, and derives a novel thresholding condition for identifying the functional sparsity at the group level, and proposes an efficient block coordinate descent algorithm for constructing the estimate.