6 citations · 11 across the 7 of their papers we have counts for
7 papers
Disentangling impact of capacity, objective, batchsize, estimators, and step-size on flow VI
Abhinav Agrawal, Justin Domke
Normalizing flow-based variational inference (flow VI) is a promising approximate inference approach, but its performance remains inconsistent across studies. Numerous algorithmic…
Understanding and mitigating difficulties in posterior predictive evaluation
Abhinav Agrawal, Justin Domke
Predictive posterior densities (PPDs) are of interest in approximate Bayesian inference. Typically, these are estimated by simple Monte Carlo (MC) averages using samples from the a…
Can AI Models Appreciate Document Aesthetics? An Exploration of Legibility and Layout Quality in Relation to Prediction Confidence
Hsiu-Wei Yang, Abhinav Agrawal, Pavlos Fragkogiannis +1
A well-designed document communicates not only through its words but also through its visual eloquence. Authors utilize aesthetic elements such as colors, fonts, graphics, and layo…
Extracting Complex Named Entities in Legal Documents via Weakly Supervised Object Detection
Hsiu-Wei Yang, Abhinav Agrawal
Accurate Named Entity Recognition (NER) is crucial for various information retrieval tasks in industry. However, despite significant progress in traditional NER methods, the extrac…
Amortized Variational Inference for Simple Hierarchical Models
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. Thus, inference in hierarch…
Normalizing Flows Across Dimensions
Edmond Cunningham, Renos Zabounidis, Abhinav Agrawal +2
Real-world data with underlying structure, such as pictures of faces, are hypothesized to lie on a low-dimensional manifold. This manifold hypothesis has motivated state-of-the-art…
Advances in Black-Box VI: Normalizing Flows, Importance Weighting, and Optimization
Abhinav Agrawal, Daniel Sheldon, Justin Domke
Recent research has seen several advances relevant to black-box VI, but the current state of automatic posterior inference is unclear. One such advance is the use of normalizing fl…