Search Results for author: Du Phan

Found 6 papers, 3 papers with code

Reparameterized Variational Rejection Sampling

no code implementations26 Sep 2023 Martin Jankowiak, Du Phan

To expand the space of flexible variational families, we revisit Variational Rejection Sampling (VRS) [Grover et al., 2018], which combines a parametric proposal distribution with rejection sampling to define a rich non-parametric family of distributions that explicitly utilizes the known target distribution.

Variational Inference

On Uncertainty Calibration and Selective Generation in Probabilistic Neural Summarization: A Benchmark Study

no code implementations17 Apr 2023 Polina Zablotskaia, Du Phan, Joshua Maynez, Shashi Narayan, Jie Ren, Jeremiah Liu

Modern deep models for summarization attains impressive benchmark performance, but they are prone to generating miscalibrated predictive uncertainty.

Probabilistic Deep Learning

Surrogate Likelihoods for Variational Annealed Importance Sampling

no code implementations22 Dec 2021 Martin Jankowiak, Du Phan

Variational inference is a powerful paradigm for approximate Bayesian inference with a number of appealing properties, including support for model learning and data subsampling.

Probabilistic Programming Variational Inference

Composable Effects for Flexible and Accelerated Probabilistic Programming in NumPyro

3 code implementations24 Dec 2019 Du Phan, Neeraj Pradhan, Martin Jankowiak

NumPyro is a lightweight library that provides an alternate NumPy backend to the Pyro probabilistic programming language with the same modeling interface, language primitives and effect handling abstractions.

Probabilistic Programming

Functional Tensors for Probabilistic Programming

1 code implementation23 Oct 2019 Fritz Obermeyer, Eli Bingham, Martin Jankowiak, Du Phan, Jonathan P. Chen

It is a significant challenge to design probabilistic programming systems that can accommodate a wide variety of inference strategies within a unified framework.

Probabilistic Programming

Cannot find the paper you are looking for? You can Submit a new open access paper.