English
Related papers

Related papers: Operator learning without the adjoint

200 papers

We show that a simplified version of the Dirac interaction operator given by $\hat H_\mathrm{I} \propto \int d\mathbf{k}d\mathbf{p}(\hat a(\mathbf{k}) + \hat a^\dagger(-\mathbf{k})) \hat b^\dagger(\mathbf{p} + \mathbf{k}) \hat…

Quantum Physics · Physics 2024-01-24 Mads J. Damgaard

Training-free diffusion priors enable inverse-problem solvers without retraining, but for nonlinear forward operators data consistency often relies on repeated derivatives or inner optimization/MCMC loops with conservative step sizes,…

Machine Learning · Computer Science 2026-04-15 Minwoo Kim , Seunghyeok Shin , Hongki Lim

In this paper we explore a certain class of non-selfadjoint operators acting in a complex separable Hilbert space. We consider a perturbation of a non-selfadjoint operator by an operator that is also non-selfadjoint. Our consideration is…

Functional Analysis · Mathematics 2019-03-26 M. V. Kukushkin

A parametric class of trust-region algorithms for unconstrained nonconvex optimization is considered where the value of the objective function is never computed. The class contains a deterministic version of the first-order Adagrad method…

Optimization and Control · Mathematics 2023-06-08 S. Gratton , S. Jerad , Ph. L. Toint

This is a review of some coordinate-free calculi of pseudodifferential operators developed in the last years. As an application, we use a coordinate-free calculus to obtain new results on the behaviour of the spectral projections of a…

Analysis of PDEs · Mathematics 2011-06-21 P. Mckeag , Y. Safarov

A recent paper by Boughammoura (2023) describes the back-propagation algorithm in terms of an alternative formulation called the F-adjoint method. In particular, by the F-adjoint algorithm the computation of the loss gradient, with respect…

Machine Learning · Computer Science 2024-07-17 Ahmed Boughammoura

In high-stakes AI applications, even a single action can cause irreparable damage. However, nearly all of sequential decision-making theory assumes that all errors are recoverable (e.g., by bounding rewards). Standard bandit algorithms that…

Machine Learning · Computer Science 2026-04-14 Sarah Liaw , Benjamin Plaut

The central problem we consider is the distribution of eigenvalues of closed linear operators which are not selfadjoint, with a focus on those operators which are obtained as perturbations of selfadjoint linear operators. Two methods are…

Spectral Theory · Mathematics 2014-03-25 Michael Demuth , Marcel Hansmann , Guy Katriel

A new technique for approximating eigenvalues and eigenvectors of a self-adjoint operator is presented. The method does not incur spectral pollution, uses trial spaces from the form domain, has a self-adjoint algorithm, and exhibits…

Spectral Theory · Mathematics 2014-03-28 Michael Strauss

The aim of the paper is to obtain a description of the selfadjoint subspace of the one-speed Boltzmann operator. It is proved that this subspace is nontrivial if the collision integral is polynomial and the multiplication coefficient has a…

Spectral Theory · Mathematics 2009-10-22 Roman Romanov , Michael Tihomirov

We discuss the possibility to learn a data-driven explicit model correction for inverse problems and whether such a model correction can be used within a variational framework to obtain regularised reconstructions. This paper discusses the…

Numerical Analysis · Mathematics 2020-10-22 Sebastian Lunz , Andreas Hauptmann , Tanja Tarvainen , Carola-Bibiane Schönlieb , Simon Arridge

We investigate the rational approximation of fractional powers of unbounded positive operators attainable with a specific integral representation of the operator function. We provide accurate error bounds by exploiting classical results in…

Numerical Analysis · Mathematics 2024-03-19 Lidia Aceto , Paolo Novati

An adaptive regularization algorithm for unconstrained nonconvex optimization is presented in which the objective function is never evaluated, but only derivatives are used. This algorithm belongs to the class of adaptive regularization…

Optimization and Control · Mathematics 2022-05-05 S. Gratton , S. Jerad , Ph. L. Toint

We study the essential self-adjointness for real principal type differential operators. Unlike the elliptic case, we need geometric conditions even for operators on the Euclidean space with asymptotically constant coefficients, and we prove…

Analysis of PDEs · Mathematics 2019-12-13 Shu Nakamura , Kouichi Taira

Distinguished selfadjoint extensions of operators which are not semibounded can be deduced from the positivity of the Schur Complement (as a quadratic form). In practical applications this amounts to proving a Hardy-like inequality.…

Analysis of PDEs · Mathematics 2017-08-23 Maria J. Esteban , Michael Loss

Over the past few years, the federated learning ($\texttt{FL}$) community has witnessed a proliferation of new $\texttt{FL}$ algorithms. However, our understating of the theory of $\texttt{FL}$ is still fragmented, and a thorough, formal…

Machine Learning · Computer Science 2025-05-23 Saber Malekmohammadi , Kiarash Shaloudegi , Zeou Hu , Yaoliang Yu

We provide a simple recipe for obtaining all self-adjoint extensions, together with their resolvent, of the symmetric operator $S$ obtained by restricting the self-adjoint operator $A:\D(A)\subseteq\H\to\H$ to the dense, closed with respect…

Mathematical Physics · Physics 2008-03-28 Andrea Posilicano

We prove a semiclassical resolvent estimate for a broad class of non-self-adjoint, non-elliptic pseudodifferential operators in the low-lying spectral regime. The proof relies on improved ellipticity properties for the symbol of the…

Spectral Theory · Mathematics 2026-01-27 Stepan Malkov

This text is a survey of recent results obtained by the author and collaborators on different problems for non-self-adjoint operators. The topics are: Kramers-Fokker-Planck type operators, spectral asymptotics in two dimensions and Weyl…

Spectral Theory · Mathematics 2008-04-24 Johannes Sjoestrand

The paper contributes to strengthening the relation between machine learning and the theory of differential equations. In this context, the inverse problem of fitting the parameters, and the initial condition of a differential equation to…

Machine Learning · Computer Science 2022-06-22 Imre Fekete , András Molnár , Péter L. Simon