242 citations · 294 across the 6 of their papers we have counts for
6 papers
Reparameterized Variational Rejection Sampling
Martin Jankowiak, Du Phan
Traditional approaches to variational inference rely on parametric families of variational distributions, with the choice of family playing a critical role in determining the accur…
On Uncertainty Calibration and Selective Generation in Probabilistic Neural Summarization: A Benchmark Study
Polina Zablotskaia, Du Phan, Joshua Maynez +3
Modern deep models for summarization attains impressive benchmark performance, but they are prone to generating miscalibrated predictive uncertainty. This means that they assign hi…
Plex: Towards Reliability using Pretrained Large Model Extensions
Dustin Tran, Jeremiah Liu, Michael W. Dusenberry +23
A recent trend in artificial intelligence is the use of pretrained models for language and vision tasks, which have achieved extraordinary performance but also puzzling failures. P…
Surrogate Likelihoods for Variational Annealed Importance Sampling
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. By…
Composable Effects for Flexible and Accelerated Probabilistic Programming in NumPyro
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 e…
Functional Tensors for Probabilistic Programming
Fritz Obermeyer, Eli Bingham, Martin Jankowiak +2
It is a significant challenge to design probabilistic programming systems that can accommodate a wide variety of inference strategies within a unified framework. Noting that the ve…