Soft-Constrained Optimization of Latent Space in Variational Autoencoders
Ye Shi
cs.LG, stat.ML
Submitted: 2026-07-26
Comments: 12 figures, 7 tables
Code: https://github.com/deepmind/dsprites-dataset
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Auto-Encoding Variational Bayes
- Lossy Image Compression with Compressive Autoencoders
- Towards a Definition of Disentangled Representations
- InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets
- Sample-Efficient Optimization in the Latent Space of Deep Generative Models via Weighted Retraining
- Optimizing the Latent Space of Generative Networks
- Spectral Norm Regularization for Improving the Generalizability of Deep Learning
- End-to-End Constrained Optimization Learning: A Survey
- Understanding disentangling in $\beta$-VAE
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks