Beyond Unimodal Bases: Pullback Geometry for Multimodal Data
cs.LG
Submitted: 2026-09-30
Updated: 2026-09-30
Sources
- Pulling back symmetric Riemannian geometry for data analysis
- Riemannian Archetypal Analysis: Interpretable non-linear data analysis on deformed star distributions
- Iso-Riemannian Optimization on Learned Data Manifolds
- Riemannian Metric Matching for Scalable Geometric Modeling of Distributions
- Deep Unsupervised Clustering with Gaussian Mixture Variational Autoencoders
- Density estimation on smooth manifolds with normalizing flows
- Learning Distances from Data with Normalizing Flows and Score Matching
- Manifold Learning with Normalizing Flows: Towards Regularity, Expressivity and Iso-Riemannian Geometry
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