mlsanityData to 13 Oct 2026

Balancing reconstruction error and Kullback-Leibler divergence in Variational Autoencoders

arXiv 2002.07514 ↗First posted 18 Feb 2020cs.NE cs.LGcited by 30

Not on the map. Why?

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.

Key facts. Cited by 30 papers in the map (data through 13 Oct 2026). First posted on arXiv 18 Feb 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 13 Oct)

Citing papers per year: 2021: 6; 2022: 6; 2023: 5; 2024: 3; 2025: 7; 2026: 3.

30 papers.

Sort:

By area:

  1. 2021A survey on Variational Autoencoders from a GreenAI perspectivecited by 22
  2. 2024Topic Modeling as Multi-Objective Contrastive Optimizationcited by 12
  3. 2022Comparing the latent space of generative modelscited by 11
  4. 2023Multi-modal Latent Diffusioncited by 9
  5. 2023Novelty Detection in Reinforcement Learning with World Modelscited by 8
  6. 2022Optimizing Training Trajectories in Variational Autoencoders via Latent Bayesian Optimization Approachcited by 7
  7. 2023Combining Variational Autoencoders and Physical Bias for Improved Microscopy Data Analysiscited by 5
  8. 2025WQLCP: Weighted Adaptive Conformal Prediction for Robust Uncertainty Quantification Under Distribution Shiftscited by 5
  9. 2022Disentangling Autoencoders (DAE)cited by 3
  10. 2021Rapid parameter estimation of discrete decaying signals using autoencoder networkscited by 2
  11. 2022Training β-VAE by Aggregating a Learned Gaussian Posterior with a Decoupled Decodercited by 2
  12. 2025BN-Pool: Bayesian Nonparametric Pooling for Graphscited by 2
18 more
  1. 2025A Comprehensive Survey on Network Traffic Synthesis: From Statistical Models to Deep Learningcited by 2
  2. 2021Hierarchical Variational Autoencoder for Visual Counterfactualscited by 1
  3. 2021Dynamic β-VAEs for quantifying biodiversity by clustering optically recorded insect signalscited by 1
  4. 2022Enhancing variational generation through self-decompositioncited by 1
  5. 2023A Generative Neural Network Approach for 3D Multi-Criteria Design Generation and Optimization of an Engine Mount for an Unmanned Air Vehiclecited by 1
  6. 2024A Generative Framework for Predictive Modeling of Multiple Chronic Conditions Using Graph Variational Autoencoder and Bandit-Optimized Graph Neural Networkcited by 1
  7. 2021A Deep Learning Generative Model Approach for Image Synthesis of Plant Leavescited by 0
  8. 2021Automatically detecting anomalous exoplanet transitscited by 0
  9. 2022KL Regularized Normalization Framework for Low Resource Taskscited by 0
  10. 2023SEER-ZSL: Semantic Encoder-Enhanced Representations for Generalized Zero-Shot Learningcited by 0
  11. 2024Advancing Generative Model Evaluation: A Novel Algorithm for Realistic Image Synthesis and Comparison in OCR Systemcited by 0
  12. 2025Improving Inference-Time Optimisation for Vocal Effects Style Transfer with a Gaussian Priorcited by 0
  13. 2025Denoising diffusion models for inverse design of inflatable structures with programmable deformationscited by 0
  14. 2025LatentFlow: Cross-Frequency Experimental Flow Reconstruction from Sparse Pressure via Latent Mappingcited by 0
  15. 2025An Efficient 3D Latent Diffusion Model for T1-contrast Enhanced MRI Generationcited by 0
  16. 2026Generative Augmentation of Raman Spectra for Glioma Classificationcited by 0
  17. 2026Soft-Constrained Optimization of Latent Space in Variational Autoencoderscited by 0
  18. 2026Weakly supervised concept Bottleneck Learning for Robust Two stage Object centric visual reasoningcited by 0