English
Related papers

Related papers: Measuring Complexity of Learning Schemes Using Hes…

200 papers

We introduce a novel family of invariant, convex, and non-quadratic functionals that we employ to derive regularized solutions of ill-posed linear inverse imaging problems. The proposed regularizers involve the Schatten norms of the Hessian…

Optimization and Control · Mathematics 2014-02-20 Stamatios Lefkimmiatis , John Paul Ward , Michael Unser

In recent years, total variation (TV) and Euler's elastica (EE) have been successfully applied to image processing tasks such as denoising and inpainting. This paper investigates how to extend TV and EE to the supervised learning settings…

Machine Learning · Computer Science 2012-06-22 Tong Lin , Hanlin Xue , Ling Wang , Hongbin Zha

Recently, there has been a surge in interest in developing optimization algorithms for overparameterized models as achieving generalization is believed to require algorithms with suitable biases. This interest centers on minimizing…

Machine Learning · Computer Science 2026-02-05 Behrooz Tahmasebi , Ashkan Soleymani , Dara Bahri , Stefanie Jegelka , Patrick Jaillet

Conventional model-based image denoising optimizations employ convex regularization terms, such as total variation (TV) that convexifies the $\ell_0$-norm to promote sparse signal representation. Instead, we propose a new non-convex total…

Image and Video Processing · Electrical Eng. & Systems 2025-06-04 Songlin Wei , Gene Cheung , Fei Chen , Ivan Selesnick

We consider the problem of estimating a regression function in the common situation where the number of features is small, where interpretability of the model is a high priority, and where simple linear or additive models fail to provide…

Machine Learning · Statistics 2017-08-08 Wesley Tansey , Jesse Thomason , James G. Scott

In graph signal processing, learning the weighted connections between nodes from a set of sample signals is a fundamental task when the underlying relationships are not known a priori. This task is typically addressed by finding a graph…

Machine Learning · Computer Science 2025-06-30 Benjamin T. Brown , Haoxiang Zhang , Daniel L. Lau , Gonzalo R. Arce

We introduce semi-supervised data classification algorithms based on total variation (TV), Reproducing Kernel Hilbert Space (RKHS), support vector machine (SVM), Cheeger cut, labeled and unlabeled data points. We design binary and…

Machine Learning · Computer Science 2012-10-03 Xavier Bresson , Ruiliang Zhang

This paper proposes a unified framework for the investigation of constrained learning theory in reflexive Banach spaces of features via regularized empirical risk minimization. The focus is placed on Tikhonov-like regularization with…

Statistics Theory · Mathematics 2016-10-20 Patrick L. Combettes , Saverio Salzo , Silvia Villa

Over the last decades, the total variation (TV) evolved to one of the most broadly-used regularisation functionals for inverse problems, in particular for imaging applications. When first introduced as a regulariser, higher-order…

Optimization and Control · Mathematics 2020-12-30 Kristian Bredies , Martin Holler

Hyperspectral images (HSIs) are often corrupted by a mixture of several types of noise during the acquisition process, e.g., Gaussian noise, impulse noise, dead lines, stripes, and many others. Such complex noise could degrade the quality…

Computer Vision and Pattern Recognition · Computer Science 2017-07-11 Yao Wang , Jiangjun Peng , Qian Zhao , Deyu Meng , Yee Leung , Xi-Le Zhao

Flatness measures based on the spectrum or the trace of the Hessian of the loss are widely used as proxies for the generalization ability of deep networks. However, most existing definitions are either tailored to fully connected…

Machine Learning · Computer Science 2026-03-11 Rahman Taleghani , Maryam Mohammadi , Francesco Marchetti

In this paper we analyze in detail a few questions related to the theory of functions with bounded $p$-Hessian-Schatten total variation, which are relevant in connection with the theory of inverse problems and machine learning. We prove an…

Functional Analysis · Mathematics 2023-02-27 Luigi Ambrosio , Camillo Brena , Sergio Conti

In this work, a novel algorithm called SVM with Shape-adaptive Reconstruction and Smoothed Total Variation (SaR-SVM-STV) is introduced to classify hyperspectral images, which makes full use of spatial and spectral information. The…

Computer Vision and Pattern Recognition · Computer Science 2022-04-15 Ruoning Li , Kangning Cui , Raymond H. Chan , Robert J. Plemmons

Total Variation regularization (TV) is a seminal approach for image recovery. TV involves the norm of the image's gradient, aggregated over all pixel locations. Therefore, TV leads to piece-wise constant solutions, resulting in what is…

Optimization and Control · Mathematics 2023-09-12 Manu Ghulyani , Muthuvel Arigovindan

In this paper, a variational, multi-dimensional model for image reconstruction is proposed, in which the regularization term consists of the $r$-order (an)-isotropic total variation seminorms $TV^r$, with $r\in \mathbb R^+$, defined via the…

Analysis of PDEs · Mathematics 2019-01-17 Pan Liu , Xin Yang Lu

In this paper, we propose a regularization technique for noisy-image super-resolution and image denoising. Total variation (TV) regularization is adopted in many image processing applications to preserve the local smoothness. However, TV…

Image and Video Processing · Electrical Eng. & Systems 2022-02-23 Kaicong Sun , Sven Simon

Random features is a powerful universal function approximator that inherits the theoretical rigor of kernel methods and can scale up to modern learning tasks. This paper views uncertain system models as unknown or uncertain smooth functions…

Machine Learning · Computer Science 2021-06-25 Diego Agudelo-España , Yassine Nemmour , Bernhard Schölkopf , Jia-Jie Zhu

Over the last 30 years a plethora of variational regularisation models for image reconstruction has been proposed and thoroughly inspected by the applied mathematics community. Among them, the pioneering prototype often taught and learned…

Numerical Analysis · Mathematics 2021-04-09 Monica Pragliola , Luca Calatroni , Alessandro Lanza , Fiorella Sgallari

Solving computer vision problems through machine learning, one often encounters lack of sufficient training data. To mitigate this we propose the use of ensembles of weak learners based on spectral total-variation (STV) features (Gilboa…

Computer Vision and Pattern Recognition · Computer Science 2025-07-14 Anna Rosenberg , John Kennedy , Zohar Keidar , Yehoshua Y. Zeevi , Guy Gilboa

For image denoising problems, the structure tensor total variation (STV)-based models show good performances when compared with other competing regularization approaches. However, the STV regularizer does not couple the local information of…

Optimization and Control · Mathematics 2024-04-05 Xiuhan Sheng , Lijuan Yang , Jingya Chang