Fisher Widths: Local Learning Geometry and Anisotropic Recovery

arXiv:2607.20578 · cs.LG, math.ST, stat.ML · Submitted 2026-07-22 · Read on arXiv

Vu Khac Ky

cs.LG, math.ST, stat.ML

Submitted: 2026-07-22

Comments: 38 pages, 3 figures

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

Terminology

• Decoder — 19× in this paper · explained in 2 episodes
• Fisher Information — 15× in this paper · explained in 4 episodes
• Anisotropy — 8× in this paper · explained in 4 episodes
• Sparsity — 7× in this paper · explained in 5 episodes
• Monotonicity — 5× in this paper · explained in 2 episodes
• Phase Transition — 4× in this paper · explained in 3 episodes
• Phase Transitions — 4× in this paper · explained in 2 episodes
• Regularization — 2× in this paper · explained in 3 episodes
• Verification — 2× in this paper · explained in 2 episodes
• Accuracy — 1× in this paper · explained in 1 episode
• Generalization — 1× in this paper · explained in 14 episodes
• Homogeneity — 1× in this paper · explained in 2 episodes
• Inverse Problem — 1× in this paper · explained in 2 episodes
• Lasso — 1× in this paper · explained in 2 episodes
• Localization — 1× in this paper · explained in 2 episodes
• Preconditioner — 1× in this paper · explained in 2 episodes
• Trace — 1× in this paper · explained in 2 episodes
• Unified Framework — 1× in this paper · explained in 6 episodes
• Universality — 1× in this paper · explained in 2 episodes

Sources

• Fisher Width: A Geometric Measure of Complexity on Statistical Manifolds

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