AI & ML
Fisher Completions and Statistical Regularization of Wrapped Gaussian Families
arXiv stat.TH0 views
arXiv:2610.37526v1 Announce Type: new Abstract: We determine the intrinsic Fisher completion of the full-covariance wrapped Gaussian family on a fixed torus and relate its geometry to uniform estimation. The completion is homeomorphic to the total-variation closure. Every added law is, in suitable integer torus coordinates, a product of a uniform law and a lower-dimensional wrapped Gaussian. All these densities are positive and real analytic, but in dimension at least two no added point has a compact neighborhood. Small balls remain contractible, and explicit minimizing geodesics pass through added points. In dimension at least two, every fixed Fisher neighborhood of an added point has a positive minimax risk at every sample size. For subfamilies with a common positive lower bound on the variance in every nonzero integer direction, we prove that compactness of the completed closure is equivalent to uniform consistency in either $L^1$ or completed-Fisher loss. Equivalently, the Fourier moments must decay uniformly over the subfamily. A fixed covariance floor guarantees this condition without an upper covariance bound and gives $L^1$ risk at most $C_{\varepsilon,d}n^{-1/2}\{\log(n+1)\}^{d/4}$. A common-phase example illustrates how partially uniform limits can retain relative-phase information while remaining uniformly estimable.
Source:https://arxiv.org/abs/2610.37526PreviousModel-based clustering of diffusion processes with constant volatility coefficients using high-frequency dataNextApproximation Families and the Statistical Efficiency of Denoising Score Matching
Related posts

Affinity’s creative studio is now available on iPad for free
0The Verge

SpaceX could buy Boost Mobile as part of its big mobile carrier plans
0The Verge
Northwood Space raises $375M Series C at a $2B valuation from a16z and DFJ growth
0TechCrunch

The Download: the agentic web arrives and the drive for safer roads
0MIT Technology Review

Stop counting tokens, start counting what ships
0MIT Technology Review
OpenAI is finally merging ChatGPT’s chat and Work tabs
0TechCrunch