Amortized Variational Inference: A Systematic Review
From MaRDI portal
Abstract: 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. With 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.
Recommendations
- scientific article; zbMATH DE number 6377992
- Variational inference in nonconjugate models
- Gauging variational inference
- Deep variational inference
- The computational asymptotics of Gaussian variational inference and the Laplace approximation
- Variational Bayesian approximation. A rigorous approach
- Optimizing Variational Representations of Divergences and Accelerating Their Statistical Estimation
- \(\alpha\)-variational inference with statistical guarantees
- Tightening bounds for variational inference by revisiting perturbation theory
Cited in
(3)
This page was built for publication: Amortized Variational Inference: A Systematic Review
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6411576)
