Spherical Cauchy Variational Autoencoders: Heavy Angular Tails and Exact KL Evaluation

arXiv:2506.21278 · stat.ML, cs.AI, cs.LG, math.ST, stat.TH · Submitted 2025-06-26 · Read on arXiv

stat.ML, cs.AI, cs.LG, math.ST, stat.TH

Submitted: 2025-06-26

Updated: 2026-09-16

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Benchmark — 31× in this paper · explained in 2 episodes
• Latent Space — 24× in this paper · explained in 7 episodes
• Robustness — 12× in this paper · explained in 5 episodes
• Loss Function — 7× in this paper · explained in 2 episodes
• Accuracy — 5× in this paper · explained in 1 episode
• Clustering — 5× in this paper · explained in 2 episodes
• Core — 5× in this paper · explained in 2 episodes
• Generative Model — 4× in this paper · explained in 2 episodes
• Generative Modeling — 4× in this paper · explained in 3 episodes
• Kullback-Leibler (KL) Divergence — 4× in this paper · explained in 3 episodes
• Latent Representation — 4× in this paper · explained in 2 episodes
• Cosine Similarity — 3× in this paper · explained in 3 episodes
• Regularization — 3× in this paper · explained in 3 episodes
• Downstream Tasks — 2× in this paper · explained in 2 episodes
• Embeddings — 2× in this paper · explained in 2 episodes
• Fidelity — 2× in this paper · explained in 2 episodes
• Generative Models — 2× in this paper · explained in 2 episodes
• Latent Representations — 2× in this paper · explained in 3 episodes
• Transformer — 2× in this paper · explained in 2 episodes
• Ambient Dimension — 1× in this paper · explained in 1 episode
• Computational overhead — 1× in this paper · explained in 2 episodes
• Consistency — 1× in this paper · explained in 3 episodes
• Hybrid Models — 1× in this paper · explained in 2 episodes
• Reconstruction Error — 1× in this paper · explained in 2 episodes
• alpha — 1× in this paper · explained in 1 episode

Sources

• Hyperspherical Variational Auto-Encoders
• Increasing Expressivity of a Hyperspherical VAE
• Reparameterization Gradients through Acceptance-Rejection Sampling Algorithms
• von Mises-Fisher Loss: An Exploration of Embedding Geometries for Supervised Learning
• An Empirical Study on Clustering Pretrained Embeddings: Is Deep Strictly Better?
• Spherical Latent Spaces for Stable Variational Autoencoders

Related papers

• Behavior of prediction performance metrics with rare events
• Optimal Estimation of Generic Dynamics by Path-Dependent Neural Jump ODEs
• A Posterior-Dynamics Framework for Imaging Inverse Problems with Pretrained Diffusion Priors
• Efficient quadratic entropy with distance sketches
• Embedding-Bias in Conditional Independence Testing
• From Log-Odds to Shapley Values: An Explanatory Geometry for the Weighted Naive Bayes Classifier