Amortized Variational Inference: A Systematic Review
Ganguly, Ankush | Jain, Sanjana | Watchareeruetai, Ukrit (a:1:{s:5:"en_US";s:6:"Sertis";})
–Journal of Artificial Intelligence Research
The core principle of Variational Inference (VI) is to convert the statistical inference problem of computing complex posterior probability densities into a tractable optimization problem. This property enables VI to be faster than several sampling-based techniques. However, the traditional VI algorithm is not scalable to large data sets and is unable to readily infer out-of-bounds data points without re-running the optimization process. Recent developments in the field, like stochastic-, black box-, and amortized-VI, have helped address these issues. Generative modeling tasks nowadays widely make use of amortized VI for its efficiency and scalability, as it utilizes a parameterized function to learn the approximate posterior density parameters. In this paper, we review the mathematical foundations of various VI techniques to form the basis for understanding amortized VI. Additionally, we provide an overview of the recent trends that address several issues of amortized VI, such as the amortization gap, generalization issues, inconsistent representation learning, and posterior collapse. Finally, we analyze alternate divergence measures that improve VI optimization.
Journal of Artificial Intelligence Research
Oct-15-2023
- Country:
- Oceania > Australia
- New South Wales > Sydney (0.04)
- North America
- United States
- Wisconsin > Dane County
- Madison (0.04)
- New York > New York County
- New York City (0.14)
- Massachusetts
- Middlesex County > Cambridge (0.04)
- Suffolk County > Boston (0.04)
- Florida
- Palm Beach County > Boca Raton (0.04)
- Orange County > Orlando (0.04)
- California
- San Francisco County > San Francisco (0.14)
- San Diego County > San Diego (0.04)
- Wisconsin > Dane County
- Puerto Rico > San Juan
- San Juan (0.04)
- Canada
- Ontario > Toronto (0.14)
- Alberta > Census Division No. 15
- Improvement District No. 9 > Banff (0.04)
- United States
- Europe
- Italy > Sardinia (0.04)
- United Kingdom > England
- Cambridgeshire > Cambridge (0.04)
- West Midlands > Birmingham (0.04)
- France > Hauts-de-France
- Denmark > Capital Region
- Copenhagen (0.04)
- Asia
- Oceania > Australia
- Genre:
- Overview (0.88)
- Instructional Material (0.67)
- Technology:
- Information Technology > Artificial Intelligence
- Natural Language (1.00)
- Representation & Reasoning
- Uncertainty > Bayesian Inference (1.00)
- Optimization (1.00)
- Machine Learning
- Statistical Learning (1.00)
- Neural Networks > Deep Learning (1.00)
- Learning Graphical Models
- Directed Networks > Bayesian Learning (1.00)
- Undirected Networks > Markov Models (0.67)
- Information Technology > Artificial Intelligence