Searcharxiv⌕ Search

arXiv subjects

Jun Tsuzurugi

Publications and source records attributed to Jun Tsuzurugi.

4 recordsLinked to original sources

Wavelet covariances under fixed finite observations: dilation symmetry breaking and distinct endpoint limits

For a centered homogeneous generalized Gaussian field with spectral weight $C|ω|^{-γ}$, we prove two-endpoint recovery of normalized posterior wavelet covariances under fixed finite admissible observations. Global dilation symmetry holds if and only if all observation functions vanish. The nonzero wavelet and the observation functions are real Schwartz functions with $M\geq1$ vanishing moments, with $C>0$ and $γ<2M+1$. Noise is Gaussian and field-independent, and total observation covariance is positive definite. Under simultaneous dilation of target scales and positions, multiplication by $λ^{-γ}$ recovers the prior covariance as $λ\downarrow0$ and $λ\uparrow\infty$, uniformly on every fixed compact target set. If a nonzero observation function exists, additional finite first nonzero Fourier orders $m_ψ,m_i$ at zero of the wavelet and nonzero observation functions yield compact-uniform recovery bounds $O(λ^{2m_ψ+1-γ})$ and $O(λ^{-(2\min_i m_i+1-γ)})$, with leading coefficients and cancellation-dependent improvements. The bounds are exact leading orders when their coefficients are nonzero. For the Matérn-type spectrum $S(ω)=C(κ^2+ω^2)^{-p}$, $κ>0$, $1/2<p<M+1/2$, fixed finite noisy point observations yield distinct compact-uniform limits: the homogeneous $C|ω|^{-2p}$ kernel after multiplication by $λ^{-2p}$ at small scales, and the constant-spectrum $S(0)$ kernel without normalization at large scales. A projection-norm criterion treats fixed closed observation subspaces; Mexican-hat formulas illustrate the finite-observation results.

math.ST↗

Finite-Mask Gaussian-Process Reconstruction on a Periodic Sensor Ring: Mask-Geometry Dependence, Fourier-Mode Coupling, and Posterior Trace

We analyze how an arbitrary observation mask on a finite periodic ring of equally spaced sensors affects the posterior covariance, Fourier-mode coupling, and normalized posterior trace in Gaussian-process reconstruction. Under a rotationally stationary prior and homogeneous independent measurement noise, complete observation gives independent scalar posterior formulas for the Fourier modes. For an arbitrary mask, however, the matrix $Q_M=F D_MF^\ast$ is generally non-diagonal; its off-diagonal entries are finite Fourier components of the realized mask and couple modes in the posterior precision. Consequently, masks with the same unavailable-channel fraction can have different normalized posterior traces because their geometries differ. A dimensionless 64-channel synthetic benchmark illustrates this finite-matrix effect. A circumferential array of equally spaced wall-mounted microphones at a fixed axial station of a circular fan or compressor duct provides one concrete mechanical-engineering interpretation: failed, saturated, corrupted, or dropped-out channels form the observation mask. The analysis is a finite-dimensional reference calculation under the stated rotational-stationarity and common-noise assumptions, not a performance claim for a nonuniform or unequally instrumented operating duct.

cs.IT↗

Statistical Mechanical Analysis of Gaussian Processes

In this paper, we analyze Gaussian processes using statistical mechanics. Although the input is originally multidimensional, we simplify our model by considering the input as one-dimensional for statistical mechanical analysis. Furthermore, we employ periodic boundary conditions as an additional modeling approach. By using periodic boundary conditions, we can diagonalize the covariance matrix. The diagonalized covariance matrix is then applied to Gaussian processes. This allows for a statistical mechanical analysis of Gaussian processes using the derived diagonalized matrix. We indicate that the analytical solutions obtained in this method closely match the results from simulations.

cond-mat.stat-mech↗

Statistical Mechanics of the Bayesian Image Restoration under Spatially Correlated Noise

We investigated the use of the Bayesian inference to restore noise-degraded images under conditions of spatially correlated noise. The generative statistical models used for the original image and the noise were assumed to obey multi-dimensional Gaussian distributions whose covariance matrices are translational invariant. We derived an exact description to be used as the expectation for the restored image by the Fourier transformation and restored an image distorted by spatially correlated noise by using a spatially uncorrelated noise model. We found that the resulting hyperparameter estimations for the minimum error and maximal posterior marginal criteria did not coincide when the generative probabilistic model and the model used for restoration were in different classes, while they did coincide when they were in the same class.

cond-mat.dis-nn↗