no code implementations • 18 Mar 2024 • Luhuan Wu, Sinead Williamson
In this paper, we approach the problem of uncertainty quantification in deep learning through a predictive framework, which captures uncertainty in model parameters by specifying our assumptions about the predictive distribution of unseen future data.
1 code implementation • 30 Nov 2022 • Gabriel Loaiza-Ganem, Brendan Leigh Ross, Luhuan Wu, John P. Cunningham, Jesse C. Cresswell, Anthony L. Caterini
Likelihood-based deep generative models have recently been shown to exhibit pathological behaviour under the manifold hypothesis as a consequence of using high-dimensional densities to model data with low-dimensional structure.
no code implementations • 3 Feb 2022 • Luhuan Wu, Geoff Pleiss, John Cunningham
Variational approximations to Gaussian processes (GPs) typically use a small set of inducing points to form a low-rank approximation to the covariance matrix.
1 code implementation • 28 Feb 2021 • Luhuan Wu, Andrew Miller, Lauren Anderson, Geoff Pleiss, David Blei, John Cunningham
In this work, we introduce the hierarchical inducing point GP (HIP-GP), a scalable inter-domain GP inference method that enables us to improve the approximation accuracy by increasing the number of inducing points to the millions.
1 code implementation • 12 Feb 2021 • Andres Potapczynski, Luhuan Wu, Dan Biderman, Geoff Pleiss, John P. Cunningham
In the case of RFF, we show that the bias-to-variance conversion is indeed a trade-off: the additional variance proves detrimental to optimization.
1 code implementation • 20 Sep 2019 • Antonio Khalil Moretti, Zizhao Wang, Luhuan Wu, Iddo Drori, Itsik Pe'er
We apply SVO to three nonlinear latent dynamics tasks and provide statistics to rigorously quantify the predictions of filtered and smoothed objectives.
no code implementations • ICLR Workshop DeepGenStruct 2019 • Antonio Moretti, Zizhao Wang, Luhuan Wu, Itsik Pe'er
The task of recovering nonlinear dynamics and latent structure from a population recording is a challenging problem in statistical neuroscience motivating the development of novel techniques in time series analysis.