We review basic notions in the field of information geometry such as Fisher metric on statistical manifold, -connection and corresponding curvature following Amari's work . We show application of information geometry to asymptotic statistical inference.
arXiv research
A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
Trend · papers per month
We prove that complete Riemannian manifolds with polynomial growth and Ricci curvature bounded from below, admit uniform Poincaré inequalities. A global, uniform Poincaré inequality for horospheres in the universal cover of a closed, -dimensional Riemannian manifold with pinched negative sectional curvature follows …
We study the prescribed scalar curvature problem, namely finding which function can be obtained as the scalar curvature of a metric in a given conformal class. We deal with the case of asymptotically hyperbolic manifolds and restrict ourselves to non positive prescribed scalar curvature. Following earlier results, we o…
SGD without replacement decouples into curvature-following and flatness-regularizing steps.
Obstructs complete metrics with positive scalar curvature on non-compact manifolds.
Study local foliations of surfaces with constant mean curvature and constant expansion in space-time.
The paper tackles Kakeya and Nikodym sets on curved manifolds, reducing problems to Euclidean space.