Picture for Gregory Wornell

Gregory Wornell

Reliable Gradient-free and Likelihood-free Prompt Tuning

Apr 30, 2023
Maohao Shen, Soumya Ghosh, Prasanna Sattigeri, Subhro Das, Yuheng Bu, Gregory Wornell

Figure 1 for Reliable Gradient-free and Likelihood-free Prompt Tuning

Figure 2 for Reliable Gradient-free and Likelihood-free Prompt Tuning

Figure 3 for Reliable Gradient-free and Likelihood-free Prompt Tuning

Figure 4 for Reliable Gradient-free and Likelihood-free Prompt Tuning

* EACL 2023 (Findings)

Access Paper or Ask Questions

On the Generalization Error of Meta Learning for the Gibbs Algorithm

Apr 27, 2023
Yuheng Bu, Harsha Vardhan Tetali, Gholamali Aminian, Miguel Rodrigues, Gregory Wornell

Figure 1 for On the Generalization Error of Meta Learning for the Gibbs Algorithm

Figure 2 for On the Generalization Error of Meta Learning for the Gibbs Algorithm

* Accepted at ISIT 2023

Access Paper or Ask Questions

Post-hoc Uncertainty Learning using a Dirichlet Meta-Model

Dec 14, 2022
Maohao Shen, Yuheng Bu, Prasanna Sattigeri, Soumya Ghosh, Subhro Das, Gregory Wornell

Figure 1 for Post-hoc Uncertainty Learning using a Dirichlet Meta-Model

Figure 2 for Post-hoc Uncertainty Learning using a Dirichlet Meta-Model

Figure 3 for Post-hoc Uncertainty Learning using a Dirichlet Meta-Model

Figure 4 for Post-hoc Uncertainty Learning using a Dirichlet Meta-Model

* Accepted by AAAI 2023

Access Paper or Ask Questions

Tighter Expected Generalization Error Bounds via Convexity of Information Measures

Feb 24, 2022
Gholamali Aminian, Yuheng Bu, Gregory Wornell, Miguel Rodrigues

Figure 1 for Tighter Expected Generalization Error Bounds via Convexity of Information Measures

* 10 pages, 1 figure

Access Paper or Ask Questions

Characterizing the Generalization Error of Gibbs Algorithm with Symmetrized KL information

Jul 28, 2021
Gholamali Aminian, Yuheng Bu, Laura Toni, Miguel R. D. Rodrigues, Gregory Wornell

* The first and second author have contributed equally to the paper. This paper is accepted in the ICML-21 Workshop on Information-Theoretic Methods for Rigorous, Responsible, and Reliable Machine Learning: https://sites.google.com/view/itr3/schedule

Access Paper or Ask Questions

Co-regularized Alignment for Unsupervised Domain Adaptation

Nov 13, 2018
Abhishek Kumar, Prasanna Sattigeri, Kahini Wadhawan, Leonid Karlinsky, Rogerio Feris, William T. Freeman, Gregory Wornell

Figure 1 for Co-regularized Alignment for Unsupervised Domain Adaptation

Figure 2 for Co-regularized Alignment for Unsupervised Domain Adaptation

Figure 3 for Co-regularized Alignment for Unsupervised Domain Adaptation

Figure 4 for Co-regularized Alignment for Unsupervised Domain Adaptation

* NIPS 2018 accepted version

Access Paper or Ask Questions