activity
20172020
most citedSimple and Principled Uncertainty Estimation with Deterministic Deep Learning via Distance Awareness

103 citations · 144 across the 8 of their papers we have counts for

collaborators

10 papers

cs.CL2020★ 4 cited

Pruning Redundant Mappings in Transformer Models via Spectral-Normalized Identity Prior

Zi Lin, Jeremiah Zhe Liu, Zi Yang +2

Traditional (unstructured) pruning methods for a Transformer model focus on regularizing the individual weights by penalizing them toward zero. In this work, we explore spectral-no…

cs.LG2020★ 30 cited

Training independent subnetworks for robust prediction

Marton Havasi, Rodolphe Jenatton, Stanislav Fort +5

Recent approaches to efficiently ensemble neural networks have shown that strong robustness and uncertainty performance can be achieved with a negligible gain in parameters over th…

cs.LG2020★ 103 cited

Simple and Principled Uncertainty Estimation with Deterministic Deep Learning via Distance Awareness

Jeremiah Zhe Liu, Zi Lin, Shreyas Padhy +3

Bayesian neural networks (BNN) and deep ensembles are principled approaches to estimate the predictive uncertainty of a deep learning model. However their practicality in real-time…

stat.ML2019★ 4 cited

Variable Selection with Rigorous Uncertainty Quantification using Deep Bayesian Neural Networks: Posterior Concentration and Bernstein-von Mises Phenomenon

Jeremiah Zhe Liu

This work develops rigorous theoretical basis for the fact that deep Bayesian neural network (BNN) is an effective tool for high-dimensional variable selection with rigorous uncert…

stat.AP2019

A Cross-validated Ensemble Approach to Robust Hypothesis Testing of Continuous Nonlinear Interactions: Application to Nutrition-Environment Studies

Jeremiah Zhe Liu, Jane Lee, Pi-i Debby Lin +6

Gene-environment and nutrition-environment studies often involve testing of high-dimensional interactions between two sets of variables, each having potentially complex nonlinear m…

math.ST2019★ 1 cited

Gaussian Process Regression and Classification under Mathematical Constraints with Learning Guarantees

Jeremiah Zhe Liu

We introduce constrained Gaussian process (CGP), a Gaussian process model for random functions that allows easy placement of mathematical constrains (e.g., non-negativity, monotoni…