English
Related papers

Related papers: Beyond Tikhonov: Faster Learning with Self-Concord…

200 papers

In this manuscript we would like to address the classical optimization problem of minimizing a proper, convex and lower semicontinuous function via the second order in time dynamics, combining viscous and Hessian-driven damping with a…

Optimization and Control · Mathematics 2023-03-20 Mikhail Karapetyants

Learning an appropriate (dis)similarity function from the available data is a central problem in machine learning, since the success of many machine learning algorithms critically depends on the choice of a similarity function to compare…

Machine Learning · Computer Science 2013-08-30 Zheng-Chu Guo , Yiming Ying

Tikhonov regularization is one of the most commonly used methods of regularization of ill-posed problems. In the setting of finite element solutions of elliptic partial differential control problems, Tikhonov regularization amounts to…

Numerical Analysis · Mathematics 2016-09-19 Erik Burman , Peter Hansbo , Mats Larson

The standard approach for dealing with the ill-posedness of the training problem in machine learning and/or the reconstruction of a signal from a limited number of measurements is regularization. The method is applicable whenever the…

Optimization and Control · Mathematics 2020-07-13 Michael Unser

In this paper, we study an explicit Tikhonov-regularized inertial gradient algorithm for smooth convex minimization with Lipschitz continuous gradient. The method is derived via an explicit time discretization of a damped inertial system…

Optimization and Control · Mathematics 2026-02-02 Samir Adly , Vinh Thanh Ho , Huu Nhan Nguyen

We present a converged algorithm for Tikhonov regularized nonnegative matrix factorization (NMF). We specially choose this regularization because it is known that Tikhonov regularized least square (LS) is the more preferable form in solving…

Machine Learning · Computer Science 2015-03-20 Andri Mirzal

We investigate the strong convergence properties of a proximal-gradient inertial algorithm with two Tikhonov regularization terms in connection to the minimization problem of the sum of a convex lower semi-continuous function $f$ and a…

Optimization and Control · Mathematics 2024-07-16 Szilárd Csaba László

We consider a statistical inverse learning problem, where we observe the image of a function $f$ through a linear operator $A$ at i.i.d. random design points $X_i$, superposed with an additive noise. The distribution of the design points is…

Machine Learning · Statistics 2016-04-15 Gilles Blanchard , Nicole Mücke

We study inverse problems F(f) = g with perturbed right hand side g^{obs} corrupted by so-called impulsive noise, i.e. noise which is concentrated on a small subset of the domain of definition of g. It is well known that Tikhonov-type…

Numerical Analysis · Mathematics 2015-04-01 Thorsten Hohage , Frank Werner

Tikhonov regularization is a popular approach to obtain a meaningful solution for ill-conditioned linear least squares problems. A relatively simple way of choosing a good regularization parameter is given by Morozov's discrepancy…

Numerical Analysis · Mathematics 2020-06-24 Jeffrey Cornelis , Nick Schenkels , Wim Vanroose

Novel Monte Carlo estimators are proposed to solve both the Tikhonov regularization (TR) and the interpolation problems on graphs. These estimators are based on random spanning forests (RSF), the theoretical properties of which enable to…

Discrete Mathematics · Computer Science 2022-03-25 Yusuf Pilavci , Pierre-Olivier Amblard , Simon Barthelme , Nicolas Tremblay

These lecture notes evolve around mathematical concepts arising in inverse problems. We start by introducing inverse problems through examples such as differentiation, deconvolution, computed tomography and phase retrieval. This then leads…

Numerical Analysis · Mathematics 2025-08-26 Danielle Bednarski , Tim Roith

Regularization plays a pivotal role in ill-posed machine learning and inverse problems. However, the fundamental comparative analysis of various regularization norms remains open. We establish a small noise analysis framework to assess the…

Machine Learning · Statistics 2024-09-05 Quanjun Lang , Fei Lu

Ensemble Kalman inversion is a parallelizable methodology for solving inverse or parameter estimation problems. Although it is based on ideas from Kalman filtering, it may be viewed as a derivative-free optimization method. In its most…

Numerical Analysis · Mathematics 2024-12-20 Neil K. Chada , Andrew M. Stuart , Xin T. Tong

It is a well-known fact that adding noise to the input data often improves network performance. While the dropout technique may be a cause of memory loss, when it is applied to recurrent connections, Tikhonov regularization, which can be…

Machine Learning · Computer Science 2017-08-11 Andrei Turkin

Continual learning, which aims to learn multiple tasks sequentially, has gained extensive attention. However, most existing work focuses on empirical studies, and the theoretical aspect remains under-explored. Recently, a few investigations…

Machine Learning · Computer Science 2025-03-25 Fei Zhu , Yujing Liu , Wenzhuo Liu , Zhaoxiang Zhang

In this paper, we study the stochastic convergence of regularized solutions for backward heat conduction problems. These problems are recognized as ill-posed due to the exponential decay of eigenvalues associated with the forward problems.…

Numerical Analysis · Mathematics 2023-11-08 Zhongjian Wang , Wenlong Zhang , Zhiwen Zhang

Conditional stability estimates allow us to characterize the degree of ill-posedness of many inverse problems, but without further assumptions they are not sufficient for the stable solution in the presence of data perturbations. We here…

Numerical Analysis · Mathematics 2018-10-17 Herbert Egger , Bernd Hofmann

In this work, we propose a new criterion for choosing the regularization parameter in Tikhonov regularization when the noise is white Gaussian. The criterion minimizes a lower bound of the predictive risk, when both data norm and noise…

Numerical Analysis · Mathematics 2020-06-24 Federico Benvenuto , Bangti Jin

We consider a distributed learning approach in supervised learning for a large class of spectral regularization methods in an RKHS framework. The data set of size n is partitioned into $m=O(n^\alpha)$ disjoint subsets. On each subset, some…

Statistics Theory · Mathematics 2017-08-10 Gilles Blanchard , Nicole Mücke