Picture for Jeremiah Zhe Liu

Jeremiah Zhe Liu

Pushing the Accuracy-Group Robustness Frontier with Introspective Self-play

Feb 11, 2023
Jeremiah Zhe Liu, Krishnamurthy Dj Dvijotham, Jihyeon Lee, Quan Yuan, Martin Strobel, Balaji Lakshminarayanan, Deepak Ramachandran

Figure 1 for Pushing the Accuracy-Group Robustness Frontier with Introspective Self-play

Figure 2 for Pushing the Accuracy-Group Robustness Frontier with Introspective Self-play

Figure 3 for Pushing the Accuracy-Group Robustness Frontier with Introspective Self-play

Figure 4 for Pushing the Accuracy-Group Robustness Frontier with Introspective Self-play

* Accepted to ICLR 2023. Included additional contribution from Martin Strobel

Access Paper or Ask Questions

A Simple Approach to Improve Single-Model Deep Uncertainty via Distance-Awareness

May 01, 2022
Jeremiah Zhe Liu, Shreyas Padhy, Jie Ren, Zi Lin, Yeming Wen, Ghassen Jerfel, Zack Nado, Jasper Snoek, Dustin Tran, Balaji Lakshminarayanan

Figure 1 for A Simple Approach to Improve Single-Model Deep Uncertainty via Distance-Awareness

Figure 2 for A Simple Approach to Improve Single-Model Deep Uncertainty via Distance-Awareness

Figure 3 for A Simple Approach to Improve Single-Model Deep Uncertainty via Distance-Awareness

Figure 4 for A Simple Approach to Improve Single-Model Deep Uncertainty via Distance-Awareness

* arXiv admin note: text overlap with arXiv:2006.10108

Access Paper or Ask Questions

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

Oct 05, 2020
Zi Lin, Jeremiah Zhe Liu, Zi Yang, Nan Hua, Dan Roth

Figure 1 for Pruning Redundant Mappings in Transformer Models via Spectral-Normalized Identity Prior

Figure 2 for Pruning Redundant Mappings in Transformer Models via Spectral-Normalized Identity Prior

Figure 3 for Pruning Redundant Mappings in Transformer Models via Spectral-Normalized Identity Prior

Figure 4 for Pruning Redundant Mappings in Transformer Models via Spectral-Normalized Identity Prior

* Findings of EMNLP 2020

Access Paper or Ask Questions

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

Dec 03, 2019
Jeremiah Zhe Liu

Figure 1 for Variable Selection with Rigorous Uncertainty Quantification using Deep Bayesian Neural Networks: Posterior Concentration and Bernstein-von Mises Phenomenon

Figure 2 for Variable Selection with Rigorous Uncertainty Quantification using Deep Bayesian Neural Networks: Posterior Concentration and Bernstein-von Mises Phenomenon

Figure 3 for Variable Selection with Rigorous Uncertainty Quantification using Deep Bayesian Neural Networks: Posterior Concentration and Bernstein-von Mises Phenomenon

Figure 4 for Variable Selection with Rigorous Uncertainty Quantification using Deep Bayesian Neural Networks: Posterior Concentration and Bernstein-von Mises Phenomenon

Access Paper or Ask Questions

Gaussian Process Regression and Classification under Mathematical Constraints with Learning Guarantees

Apr 21, 2019
Jeremiah Zhe Liu

Access Paper or Ask Questions