no code implementations • Findings (ACL) 2022 • Zi Lin, Jeremiah Zhe Liu, Jingbo Shang
Recent work in task-independent graph semantic parsing has shifted from grammar-based symbolic approaches to neural models, showing strong performance on different types of meaning representations.
no code implementations • 13 Feb 2023 • James Urquhart Allingham, Jie Ren, Michael W Dusenberry, Xiuye Gu, Yin Cui, Dustin Tran, Jeremiah Zhe Liu, Balaji Lakshminarayanan
In particular, we ask "Given a large pool of prompts, can we automatically score the prompts and ensemble those that are most suitable for a particular downstream dataset, without needing access to labeled validation data?".
no code implementations • 11 Feb 2023 • Jeremiah Zhe Liu, Krishnamurthy Dj Dvijotham, Jihyeon Lee, Quan Yuan, Martin Strobel, Balaji Lakshminarayanan, Deepak Ramachandran
Standard empirical risk minimization (ERM) training can produce deep neural network (DNN) models that are accurate on average but under-perform in under-represented population subgroups, especially when there are imbalanced group distributions in the long-tailed training data.
2 code implementations • 1 May 2022 • Jeremiah Zhe Liu, Shreyas Padhy, Jie Ren, Zi Lin, Yeming Wen, Ghassen Jerfel, Zack Nado, Jasper Snoek, Dustin Tran, Balaji Lakshminarayanan
The most popular approaches to estimate predictive uncertainty in deep learning are methods that combine predictions from multiple neural networks, such as Bayesian neural networks (BNNs) and deep ensembles.
no code implementations • 15 Apr 2022 • Wenying Deng, Beau Coker, Rajarshi Mukherjee, Jeremiah Zhe Liu, Brent A. Coull
We develop a simple and unified framework for nonlinear variable selection that incorporates uncertainty in the prediction function and is compatible with a wide range of machine learning models (e. g., tree ensembles, kernel methods, neural networks, etc).
2 code implementations • ICLR 2021 • Marton Havasi, Rodolphe Jenatton, Stanislav Fort, Jeremiah Zhe Liu, Jasper Snoek, Balaji Lakshminarayanan, Andrew M. Dai, Dustin Tran
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 the original network.
1 code implementation • Findings of the Association for Computational Linguistics 2020 • Zi Lin, Jeremiah Zhe Liu, Zi Yang, Nan Hua, Dan Roth
Traditional (unstructured) pruning methods for a Transformer model focus on regularizing the individual weights by penalizing them toward zero.
4 code implementations • NeurIPS 2020 • Jeremiah Zhe Liu, Zi Lin, Shreyas Padhy, Dustin Tran, Tania Bedrax-Weiss, Balaji Lakshminarayanan
Bayesian neural networks (BNN) and deep ensembles are principled approaches to estimate the predictive uncertainty of a deep learning model.
no code implementations • 3 Dec 2019 • Jeremiah Zhe Liu
(2) BNN's uncertainty quantification for variable importance is rigorous, in the sense that its 95% credible intervals for variable importance indeed covers the truth 95% of the time (i. e., the Bernstein-von Mises (BvM) phenomenon).
no code implementations • NeurIPS 2019 • Jeremiah Zhe Liu, John Paisley, Marianthi-Anna Kioumourtzoglou, Brent Coull
We introduce a Bayesian nonparametric ensemble (BNE) approach that augments an existing ensemble model to account for different sources of model uncertainty.
no code implementations • 21 Apr 2019 • Jeremiah Zhe Liu
Furthermore, we show that CGP inherents the optimal theoretical properties of the Gaussian process, e. g. rates of posterior contraction, due to the fact that CGP is an Gaussian process with a more efficient model space.
no code implementations • 8 Dec 2018 • Jeremiah Zhe Liu, John Paisley, Marianthi-Anna Kioumourtzoglou, Brent A. Coull
Ensemble learning is a mainstay in modern data science practice.
no code implementations • NeurIPS 2017 • Jeremiah Zhe Liu, Brent Coull
Utilizing the theory of reproducing kernels, we reduce this hypothesis to a simple one-sided score test for a scalar parameter, develop a testing procedure that is robust against the mis-specification of kernel functions, and also propose an ensemble-based estimator for the null model to guarantee test performance in small samples.