Image de couverture de livre

Mutual Information Collapse Explains Disentanglement Failure in $β$-VAEs

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Vu, Minh, Wan, Xiaoliang, Wei, Shuangqing
Format:	Preprint
Publié:	2026
Sujets:	Machine Learning
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Coupling the reduced-order model and the generative model for an importance sampling estimator
par: Wan, Xiaoliang, et autres
Publié: (2019)

Disentangling Granularity: An Implicit Inductive Bias in Factorized VAEs
par: Chen, Zihao, et autres
Publié: (2025)

Continuous First, Discrete Later: VQ-VAEs Without Dimensional Collapse
par: Zhao, Xinyu, et autres
Publié: (2026)

A Testable Certificate for Constant Collapse in Teacher-Guided VAEs
par: Zhang, Zegu, et autres
Publié: (2026)

Explaining Representation by Mutual Information
par: Gu, Lifeng
Publié: (2021)

Pruning Deep Convolutional Neural Network Using Conditional Mutual Information
par: Vu-Van, Tien, et autres
Publié: (2024)

Explaining Grokking and Information Bottleneck through Neural Collapse Emergence
par: Sakamoto, Keitaro, et autres
Publié: (2025)

Toward Architecture-Agnostic Local Control of Posterior Collapse in VAEs
par: Song, Hyunsoo, et autres
Publié: (2025)

High-dimensional Asymptotics of VAEs: Threshold of Posterior Collapse and Dataset-Size Dependence of Rate-Distortion Curve
par: Ichikawa, Yuma, et autres
Publié: (2023)

Multiple Invertible and Partial-Equivariant Function for Latent Vector Transformation to Enhance Disentanglement in VAEs
par: Jung, Hee-Jun, et autres
Publié: (2025)

Prior Learning in Introspective VAEs
par: Athanasiadis, Ioannis, et autres
Publié: (2024)

Explaining and Preventing Alignment Collapse in Iterative RLHF
par: Gauthier, Etienne, et autres
Publié: (2026)

Information-theoretic Generalization Analysis for VQ-VAEs: A Role of Latent Variables
par: Futami, Futoshi, et autres
Publié: (2025)

Optimizing Privacy and Utility Tradeoffs for Group Interests Through Harmonization
par: Mandal, Bishwas, et autres
Publié: (2024)

Initial Exploration of Zero-Shot Privacy Utility Tradeoffs in Tabular Data Using GPT-4
par: Mandal, Bishwas, et autres
Publié: (2024)

Deep Generative Clustering with VAEs and Expectation-Maximization
par: Adipoetra, Michael, et autres
Publié: (2025)

Symmetric Equilibrium Learning of VAEs
par: Flach, Boris, et autres
Publié: (2023)

Gaussian-Mixture-Model Q-Functions for Reinforcement Learning by Riemannian Optimization
par: Vu, Minh, et autres
Publié: (2024)

Gaussian-Mixture-Model Q-Functions for Policy Iteration in Reinforcement Learning
par: Vu, Minh, et autres
Publié: (2025)

Manifold Learning by Mixture Models of VAEs for Inverse Problems
par: Alberti, Giovanni S., et autres
Publié: (2023)

Achieving Collective Welfare in Multi-Agent Reinforcement Learning via Suggestion Sharing
par: Jin, Yue, et autres
Publié: (2024)

Structured Kernel Regression VAE: A Computationally Efficient Surrogate for GP-VAEs in ICA
par: Wei, Yuan-Hao, et autres
Publié: (2025)

Adversarial Robustness of VAEs across Intersectional Subgroups
par: Ramanaik, Chethan Krishnamurthy, et autres
Publié: (2024)

Robust VAEs via Generating Process of Noise Augmented Data
par: Irobe, Hiroo, et autres
Publié: (2024)

Bounded KRnet and its applications to density estimation and approximation
par: Zeng, Li, et autres
Publié: (2023)

VAEs and GANs: Implicitly Approximating Complex Distributions with Simple Base Distributions and Deep Neural Networks -- Principles, Necessity, and Limitations
par: Wei, Yuan-Hao
Publié: (2025)

Training VAEs Under Structured Residuals
par: Dorta, Gara, et autres
Publié: (2018)

Commutator-Induced Uncertainty in VAEs
par: Dehdarirad, Tahereh, et autres
Publié: (2026)

Online reinforcement learning via sparse Gaussian mixture model Q-functions
par: Vu, Minh, et autres
Publié: (2025)

GED-Consistent Disentanglement of Aligned and Unaligned Substructures for Graph Similarity Learning
par: Zhan, Zhentao, et autres
Publié: (2025)

Latent-Constrained Conditional VAEs for Augmenting Large-Scale Climate Ensembles
par: Shelton, Jacquelyn, et autres
Publié: (2026)

Improved Variational Inference in Discrete VAEs using Error Correcting Codes
par: Martínez-García, María, et autres
Publié: (2024)

Unity by Diversity: Improved Representation Learning in Multimodal VAEs
par: Sutter, Thomas M., et autres
Publié: (2024)

Learning Energy-based Variational Latent Prior for VAEs
par: Dutta, Debottam, et autres
Publié: (2025)

Disentangling Content from Style to Overcome Shortcut Learning: A Hybrid Generative-Discriminative Learning Framework
par: Fu, Siming, et autres
Publié: (2025)

Directional Neural Collapse Explains Few-Shot Transfer in Self-Supervised Learning
par: Luthra, Achleshwar, et autres
Publié: (2026)

Feature Unlearning for Pre-trained GANs and VAEs
par: Moon, Saemi, et autres
Publié: (2023)

Out-of-Distribution Radar Detection with Complex VAEs: Theory, Whitening, and ANMF Fusion
par: Rouzoumka, Yadang Alexis, et autres
Publié: (2026)

Generative Modeling of Regular and Irregular Time Series Data via Koopman VAEs
par: Naiman, Ilan, et autres
Publié: (2023)

Improving the Generation of VAEs with High Dimensional Latent Spaces by the use of Hyperspherical Coordinates
par: Ascarate, Alejandro, et autres
Publié: (2025)