# Alpha-Beta Divergence For Variational Inference

arXiv: https://arxiv.org/abs/1805.01045 · HTML: https://mlsanity.com/paper/1805.01045/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 2 May 2018.

## Built on by (most cited first, 12 of 12)

- [InfoLM: A New Metric to Evaluate Summarization & Data2Text Generation](https://mlsanity.com/paper/2112.01589/) (2021)
- [A theoretical perspective on mode collapse in variational inference](https://mlsanity.com/paper/2410.13300/) (2024)
- [Variational Inference MPC using Tsallis Divergence](https://mlsanity.com/paper/2104.00241/) (2021)
- [Bayesian brains and the R'enyi divergence](https://mlsanity.com/paper/2107.05438/) (2021)
- [Markov Chain Score Ascent: A Unifying Framework of Variational Inference with Markovian Gradients](https://mlsanity.com/paper/2206.06295/) (2022)
- [Generalized Exponentiated Gradient Algorithms and Their Application to On-Line Portfolio Selection](https://mlsanity.com/paper/2406.00655/) (2024)
- [A note on the unique properties of the Kullback--Leibler divergence for sampling via gradient flows](https://mlsanity.com/paper/2507.04330/) (2025)
- [FlowVAT: Normalizing Flow Variational Inference with Affine-Invariant Tempering](https://mlsanity.com/paper/2505.10466/) (2025)
- [A Bayesian Deep Learning Technique for Multi-Step Ahead Solar Generation Forecasting](https://mlsanity.com/paper/2203.11379/) (2022)
- [R'enyi Neural Processes](https://mlsanity.com/paper/2405.15991/) (2024)
- [The alpha-beta divergence for real and complex data](https://mlsanity.com/paper/2508.03272/) (2025)
- [Symmetry Guarantees Statistic Recovery in Variational Inference](https://mlsanity.com/paper/2604.18310/) (2026)

## Abstract (arXiv)

This paper introduces a variational approximation framework using direct optimization of what is known as the it scale invariant Alpha-Beta divergence (sAB divergence). This new objective encompasses most variational objectives that use the Kullback-Leibler, the R'enyi or the gamma divergences. It also gives access to objective functions never exploited before in the context of variational inference. This is achieved via two easy to interpret control parameters, which allow for a smooth interpolation over the divergence space while trading-off properties such as mass-covering of a target distribution and robustness to outliers in the data. Furthermore, the sAB variational objective can be optimized directly by repurposing existing methods for Monte Carlo computation of complex variational objectives, leading to estimates of the divergence instead of variational lower bounds. We show the advantages of this objective on Bayesian models for regression problems.