# Balancing reconstruction error and Kullback-Leibler divergence in Variational Autoencoders

arXiv: https://arxiv.org/abs/2002.07514 · HTML: https://mlsanity.com/paper/2002.07514/

## Key facts

- Cited by 30 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 18 Feb 2020.

## Built on by (most cited first, 30 of 30)

- [A survey on Variational Autoencoders from a GreenAI perspective](https://mlsanity.com/paper/2103.01071/) (2021)
- [Comparing the latent space of generative models](https://mlsanity.com/paper/2207.06812/) (2022)
- [Topic Modeling as Multi-Objective Contrastive Optimization](https://mlsanity.com/paper/2402.07577/) (2024)
- [Multi-modal Latent Diffusion](https://mlsanity.com/paper/2306.04445/) (2023)
- [Novelty Detection in Reinforcement Learning with World Models](https://mlsanity.com/paper/2310.08731/) (2023)
- [Optimizing Training Trajectories in Variational Autoencoders via Latent Bayesian Optimization Approach](https://mlsanity.com/paper/2207.00128/) (2022)
- [Combining Variational Autoencoders and Physical Bias for Improved Microscopy Data Analysis](https://mlsanity.com/paper/2302.04216/) (2023)
- [WQLCP: Weighted Adaptive Conformal Prediction for Robust Uncertainty Quantification Under Distribution Shifts](https://mlsanity.com/paper/2505.19587/) (2025)
- [Disentangling Autoencoders (DAE)](https://mlsanity.com/paper/2202.09926/) (2022)
- [Rapid parameter estimation of discrete decaying signals using autoencoder networks](https://mlsanity.com/paper/2103.08663/) (2021)
- [Training β-VAE by Aggregating a Learned Gaussian Posterior with a Decoupled Decoder](https://mlsanity.com/paper/2209.14783/) (2022)
- [BN-Pool: Bayesian Nonparametric Pooling for Graphs](https://mlsanity.com/paper/2501.09821/) (2025)
- [A Comprehensive Survey on Network Traffic Synthesis: From Statistical Models to Deep Learning](https://mlsanity.com/paper/2507.01976/) (2025)
- [Hierarchical Variational Autoencoder for Visual Counterfactuals](https://mlsanity.com/paper/2102.00854/) (2021)
- [Dynamic β-VAEs for quantifying biodiversity by clustering optically recorded insect signals](https://mlsanity.com/paper/2102.05526/) (2021)
- [Enhancing variational generation through self-decomposition](https://mlsanity.com/paper/2202.02738/) (2022)
- [A Generative Neural Network Approach for 3D Multi-Criteria Design Generation and Optimization of an Engine Mount for an Unmanned Air Vehicle](https://mlsanity.com/paper/2311.03414/) (2023)
- [A Generative Framework for Predictive Modeling of Multiple Chronic Conditions Using Graph Variational Autoencoder and Bandit-Optimized Graph Neural Network](https://mlsanity.com/paper/2409.13671/) (2024)
- [A Deep Learning Generative Model Approach for Image Synthesis of Plant Leaves](https://mlsanity.com/paper/2111.03388/) (2021)
- [Automatically detecting anomalous exoplanet transits](https://mlsanity.com/paper/2111.08679/) (2021)
- [KL Regularized Normalization Framework for Low Resource Tasks](https://mlsanity.com/paper/2212.11275/) (2022)
- [SEER-ZSL: Semantic Encoder-Enhanced Representations for Generalized Zero-Shot Learning](https://mlsanity.com/paper/2312.13100/) (2023)
- [Advancing Generative Model Evaluation: A Novel Algorithm for Realistic Image Synthesis and Comparison in OCR System](https://mlsanity.com/paper/2402.17204/) (2024)
- [Improving Inference-Time Optimisation for Vocal Effects Style Transfer with a Gaussian Prior](https://mlsanity.com/paper/2505.11315/) (2025)
- [Denoising diffusion models for inverse design of inflatable structures with programmable deformations](https://mlsanity.com/paper/2508.13097/) (2025)
- [LatentFlow: Cross-Frequency Experimental Flow Reconstruction from Sparse Pressure via Latent Mapping](https://mlsanity.com/paper/2508.16648/) (2025)
- [An Efficient 3D Latent Diffusion Model for T1-contrast Enhanced MRI Generation](https://mlsanity.com/paper/2509.24194/) (2025)
- [Generative Augmentation of Raman Spectra for Glioma Classification](https://mlsanity.com/paper/2607.10196/) (2026)
- [Soft-Constrained Optimization of Latent Space in Variational Autoencoders](https://mlsanity.com/paper/2607.23751/) (2026)
- [Weakly supervised concept Bottleneck Learning for Robust Two stage Object centric visual reasoning](https://mlsanity.com/paper/2608.22584/) (2026)

## Abstract (arXiv)

In the loss function of Variational Autoencoders there is a well known tension between two components: the reconstruction loss, improving the quality of the resulting images, and the Kullback-Leibler divergence, acting as a regularizer of the latent space. Correctly balancing these two components is a delicate issue, easily resulting in poor generative behaviours. In a recent work, Dai and Wipf obtained a sensible improvement by allowing the network to learn the balancing factor during training, according to a suitable loss function. In this article, we show that learning can be replaced by a simple deterministic computation, helping to understand the underlying mechanism, and resulting in a faster and more accurate behaviour. On typical datasets such as Cifar and Celeba, our technique sensibly outperforms all previous VAE architectures.