Tangent-linearized Gaussian inference on manifolds has explicit non-asymptotic W2 stability bounds that predict a calibration transition near sqrt of the operator norm of covariance over reach approximately equal to 1/6.
Title resolution pending
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3verdicts
UNVERDICTED 3representative citing papers
Contextual PPC uses world-model score densities to impose Riemannian structure on actions, yielding a safety bound on manifold distance controlled by estimation error and barrier curvature that improves with richer context.
An overview revisits LoRA variants by categorizing advances in architectural design, efficient optimization, and applications while linking them to classical signal processing tools for principled fine-tuning.
citing papers explorer
-
Distributional Stability of Tangent-Linearized Gaussian Inference on Smooth Manifolds
Tangent-linearized Gaussian inference on manifolds has explicit non-asymptotic W2 stability bounds that predict a calibration transition near sqrt of the operator norm of covariance over reach approximately equal to 1/6.
-
Safety-Critical Contextual Control via Online Riemannian Optimization with World Models
Contextual PPC uses world-model score densities to impose Riemannian structure on actions, yielding a safety bound on manifold distance controlled by estimation error and barrier curvature that improves with richer context.
-
Low-Rank Adaptation Redux for Large Models
An overview revisits LoRA variants by categorizing advances in architectural design, efficient optimization, and applications while linking them to classical signal processing tools for principled fine-tuning.