A data-based geometric quantile loss on Hadamard spaces is defined and shown to improve on parameter-based quantiles in consistency, asymptotic normality, robustness, extreme behavior, and computability.
Some differential properties of $GL_n(\mathbb{R})$ with the trace metric
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
In this note we consider some properties of $GL_n(\mathbb{R})$ with the Semi-Riemannian structure induced by the trace metric $g$. In particular we study geodesics and curvature tensors. Moreover we prove that $GL_n$ has a suitable foliation, whose leaves are isometric to $(SL_n(\mathbb{R}), g)$, while its component of matrices with positive determinant is isometric to the Semi-Riemannian product manifold $SL_n \times \mathbb{R}$.
citation-role summary
background 1
citation-polarity summary
fields
stat.ME 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
A data-based notion of quantiles on Hadamard spaces
A data-based geometric quantile loss on Hadamard spaces is defined and shown to improve on parameter-based quantiles in consistency, asymptotic normality, robustness, extreme behavior, and computability.