Develops trace class operators and inverse Laplacian theory for infinite dimensions.
problem Understanding trace class operators and inverse Laplacian on infinite dimensional spaces.
method Presentation of trace class operators and construction of inverse Laplacian on closed manifolds.
result Original trace computations involving the inverse Laplacian on the torus.
New BNN architectures reduce computational cost for uncertainty quantification.
problem High computational cost in Bayesian neural networks.
method Partial trace-class Bayesian neural networks (PaTraC BNNs).
result Comparable uncertainty quantification with fewer parameters.
Bayesian inference for deep neural networks using trace-class priors and MLMC.
problem Efficient Bayesian inference for deep neural networks.
method Trace-class neural network priors and Multilevel Monte Carlo method.
result Optimal computational complexity for Bayesian inference of TNN models.
This work presents a parametrized family of divergences, namely Alpha-Beta Log- Determinant (Log-Det) divergences, between positive definite unitized trace class operators on a Hilbert space. This is a generalization of the Alpha-Beta Log-Determinant divergences between symmetric, positive definite matrices to the infi…
The paper studies Lévy processes on compact manifolds, proving properties of their semigroups.
problem Analyzing Lévy processes on compact Riemannian manifolds.
method Proving properties of Feller semigroups and generators on Lp spaces. result The generator has a discrete spectrum of eigenvalues and the semigroup is trace-class when the process has a non-trivial Brownian part.
Maps with many singularities found in complex space.
problem Constructing maps with singularities in complex space.
method Created a map with infinitely many Schoen-Wolfson singularities on a disc.
result Found a Ck map with smooth trace in C2. We study families of Dirac-type operators, with compatible perturbations, associated to wedge metrics on stratified spaces. We define a closed domain and, under an assumption of invertible boundary families, prove that the operators are self-adjoint and Fredholm with compact resolvents and trace-class heat kernels. We …
A cocycle Ω:P×G→H taking values in a Lie group H for a free right action of G on P defines a principal bundle Q with the structure group H over P/G. The Chern character of a vector bundle associated to Q defines then characteristic classes on X. This observation becomes useful in the case …
Infinite-dimensional SBDMs improve image generation across multiple resolutions.
problem Efficient image generation at high resolutions and across different levels.
method Developed SBDMs in infinite-dimensional setting, using trace class operators and operator networks.
result Improved efficiency and generalization across resolution levels.
Let (X,h) be a compact and irreducible Hermitian complex space of complex dimension v>1. In this paper we show that the Friedrichs extension of both the Laplace-Beltrami operator and the Hodge-Kodaira Laplacian acting on functions has discrete spectrum. Moreover we provide some estimates for the growth of the corre…
Abstract: Determinants and formulas for operators on various spaces.
problem Determinants and formulas for operators on different algebras and spaces.
method Use of Poincaré type determinants, invariant operators, and full matrix-symbols.
result Explicit formulas for determinants of elliptic operators and periodic pseudo-differential operators.
We construct a Hennings type logarithmic invariant for restricted quantum sl(2) at a 2p-th root of unity. This quantum group U is not braided, but factorizable. The invariant is defined for a pair: a 3-manifold M and a colored link L inside M. The link L is split into two parts colored…
Study on geometric Jensen-Shannon divergence for Gaussian measures in Hilbert space.
problem Computing divergence between Gaussian measures in infinite-dimensional Hilbert space.
method Closed form expression and regularization for divergence calculation.
result Closed form expression and regularization for Geometric Jensen-Shannon divergence.
Study of eta invariant for non-compact manifolds via Dirac-type operators.
problem Defining and studying the relative eta invariant for non-compact manifolds.
method Defined the relative eta function and studied its variation and gluing law.
result Shows the relative eta invariant coincides with a previously defined version.
A new model captures forward curve dynamics with stochastic volatility.
problem Modeling continuous-time evolution of forward curves in financial markets.
method Affine stochastic volatility model with modulated dynamics.
result Model allows for maturity-specific risk and volatility clustering.
This paper solves nonparametric estimation of continuous DPPs using kernel methods.
problem Estimating continuous Determinantal Point Processes (DPPs) without assuming a parametric form.
method Developed a fixed point algorithm based on a representer theorem for nonnegative functions in RKHS.
result Demonstrated a finite-dimensional problem for nonparametric MLE of continuous DPPs.
Let V⊂CPn be an irreducible complex projective variety of complex dimension v and let g be the Kähler metric on $\reg(V)$, the regular part of V, induced by the Fubini Study metric of CPn. In this setting Li and Tian proved that $W^{1,2}_0(\reg(V),g)=W^{1,2}(\reg(V…
The paper introduces Causal Neural Operators to approximate operators in stochastic analysis.
problem Leveraging temporal structure in non-linear operators for deep learning models.
method Designing a deep learning model framework for infinite-dimensional linear metric spaces.
result Causal Neural Operators can uniformly approximate Hölder or smooth trace class operators.
The paper advances U-statistics in dependent settings, improving spectral estimation and goodness-of-fit tests.
problem Non-asymptotic analysis of U-statistics in dependent Markov chain settings.
method Proved new concentration and exponential inequalities for U-statistics, applied to spectral estimation, online algorithms, and goodness-of-fit tests.
result Established new results for spectral estimation, online algorithms, and goodness-of-fit tests in Markov chain settings.
Develops hypothesis tests for conditional distributions using learning-theoretic bounds.
problem Testing differences in conditional distributions and functionals.
method Transforming learning-theoretic bounds into hypothesis tests for conditional expectations.
result Establishes comprehensive foundation for conditional testing, including theoretical guarantees and practical implementations.
New Gaussian priors for neural networks improve scalability and Bayesian inference stability.
problem Scalability and stability issues in Bayesian neural network inference.
method Introduces a new Gaussian neural network prior with decreasing variance in network width, enabling stable MCMC sampling.
result The new prior enables stable MCMC sampling for Bayesian neural network inference, improving scalability and stability.
Let (X,h) be a compact and irreducible Hermitian complex space of complex dimension m. In this paper we are interested in the Dolbeault operator acting on the space of L2 sections of the canonical bundle of reg(X), the regular part of X. More precisely let $\overline{\mathfrak{d}}_{m,0}:L^2Ω^{m,0}(reg(X),h)\…
Study convergence and approximations of entropic regularized Wasserstein distances for Gaussian and RKHS measures.
problem Convergence and approximations of entropic regularized Wasserstein distances in Gaussian and RKHS settings.
method Analysis of convergence and finite sample approximations of entropic regularized Wasserstein distances in Gaussian and RKHS settings.
result Strictly weaker convergence in 2-Sinkhorn divergence for Gaussian measures compared to exact 2-Wasserstein distance.