Fisher Width: A Geometric Measure of Complexity on Statistical Manifolds

arXiv:2606.18306 · cs.LG, stat.ML · Submitted 2026-06-16 · Read on arXiv

Vu Khac Ky

cs.LG, stat.ML

Submitted: 2026-06-16

Comments: 48 pages, 3 figures

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

Terminology

• Generalization — 30× in this paper · explained in 14 episodes
• Fisher Information — 22× in this paper · explained in 4 episodes
• Regularization — 12× in this paper · explained in 3 episodes
• Trace — 4× in this paper · explained in 2 episodes
• Verification — 4× in this paper · explained in 2 episodes
• Accuracy — 3× in this paper · explained in 1 episode
• Anisotropy — 2× in this paper · explained in 4 episodes
• Phase Transition — 2× in this paper · explained in 3 episodes
• Phase Transitions — 2× in this paper · explained in 2 episodes
• Structural Properties — 2× in this paper · explained in 2 episodes
• Generalization Bounds — 1× in this paper · explained in 2 episodes
• Hilbert Space — 1× in this paper · explained in 2 episodes
• Homogeneity — 1× in this paper · explained in 2 episodes
• Inverse Problem — 1× in this paper · explained in 2 episodes
• Kullback–Leibler Divergence — 1× in this paper · explained in 2 episodes
• Loss Function — 1× in this paper · explained in 2 episodes
• Monotonicity — 1× in this paper · explained in 2 episodes
• Monte Carlo Sampling — 1× in this paper · explained in 2 episodes
• Sample Complexity — 1× in this paper · explained in 20 episodes

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