The Implicit Bias of Hyperbolic Representation Learning for Multiclass Data: A Busemann Risk Perspective
cs.LG
Submitted: 2026-10-05
Updated: 2026-10-05
Terminology
Sources
- Understanding deep learning requires rethinking generalization
- In Search of the Real Inductive Bias: On the Role of Implicit Regularization in Deep Learning
- Poincar'e Embeddings for Learning Hierarchical Representations
- Hyperbolic Neural Networks++
- Gradient Descent Maximizes the Margin of Homogeneous Neural Networks
- Directional convergence and alignment in deep learning
- Riemannian Adaptive Optimization Methods
- Learning Continuous Hierarchies in the Lorentz Model of Hyperbolic Geometry
- Hyperspherical Prototype Networks
- Risk and parameter convergence of logistic regression
- Hyperbolic Busemann Neural Networks
- Neural Networks on Symmetric Spaces of Noncompact Type
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