no code implementations • 30 May 2024 • Abhinav Agrawal, Justin Domke
Predictive posterior densities (PPDs) are of interest in approximate Bayesian inference.
no code implementations • 27 Mar 2024 • Hsiu-Wei Yang, Abhinav Agrawal, Pavlos Fragkogiannis, Shubham Nitin Mulay
A well-designed document communicates not only through its words but also through its visual eloquence.
no code implementations • 10 May 2023 • Hsiu-Wei Yang, Abhinav Agrawal
Accurate Named Entity Recognition (NER) is crucial for various information retrieval tasks in industry.
no code implementations • NeurIPS 2021 • Abhinav Agrawal, Justin Domke
It is difficult to use subsampling with variational inference in hierarchical models since the number of local latent variables scales with the dataset.
no code implementations • 23 Jun 2020 • Edmond Cunningham, Renos Zabounidis, Abhinav Agrawal, Ina Fiterau, Daniel Sheldon
In this paper we introduce noisy injective flows (NIF), a generalization of normalizing flows that can go across dimensions.
no code implementations • NeurIPS 2020 • Abhinav Agrawal, Daniel Sheldon, Justin Domke
The combination of these algorithmic components significantly advances the state-of-the-art "out of the box" variational inference.