English
Related papers

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

200 papers

This paper is concerned with the introduction of Tikhonov regularization into least squares approximation scheme on $[-1,1]$ by orthonormal polynomials, in order to handle noisy data. This scheme includes interpolation and…

Numerical Analysis · Mathematics 2021-08-31 Congpei An , Hao-Ning Wu

The success of deep neural networks is mostly due their ability to learn meaningful features from the data. Features learned in the hidden layers of deep neural networks trained in computer vision tasks have been shown to be similar to…

Machine Learning · Computer Science 2017-01-04 Biswajit Paria , Vikas Reddy , Anirban Santara , Pabitra Mitra

We study realizable continual linear regression under random task orderings, a common setting for developing continual learning theory. In this setup, the worst-case expected loss after $k$ learning iterations admits a lower bound of…

Machine Learning · Computer Science 2025-10-28 Ran Levinstein , Amit Attia , Matan Schliserman , Uri Sherman , Tomer Koren , Daniel Soudry , Itay Evron

We provide theoretical investigation of curriculum learning in the context of stochastic gradient descent when optimizing the convex linear regression loss. We prove that the rate of convergence of an ideal curriculum learning method is…

Machine Learning · Computer Science 2023-12-29 Daphna Weinshall , Gad Cohen , Dan Amir

In this paper, an online learning algorithm is proposed as sequential stochastic approximation of a regularization path converging to the regression function in reproducing kernel Hilbert spaces (RKHSs). We show that it is possible to…

Probability · Mathematics 2013-01-23 Pierre Tarrès , Yuan Yao

State-of-the-art federated learning methods can perform far worse than their centralized counterparts when clients have dissimilar data distributions. For neural networks, even when centralized SGD easily finds a solution that is…

Machine Learning · Computer Science 2022-10-06 Yaodong Yu , Alexander Wei , Sai Praneeth Karimireddy , Yi Ma , Michael I. Jordan

Although Gaussian processes (GPs) with deep kernels have been successfully used for meta-learning in regression tasks, its uncertainty estimation performance can be poor. We propose a meta-learning method for calibrating deep kernel GPs for…

Machine Learning · Statistics 2023-12-14 Tomoharu Iwata , Atsutoshi Kumagai

A learning approach to selecting regularization parameters in multi-penalty Tikhonov regularization is investigated. It leads to a bilevel optimization problem, where the lower level problem is a Tikhonov regularized problem parameterized…

Optimization and Control · Mathematics 2018-12-05 Gernot Holler , Karl Kunisch , Richard C. Barnard

A main drawback of classical Tikhonov regularization is that often the parameters required to apply theoretical results, e.g., the smoothness of the sought-after solution and the noise level, are unknown in practice. In this paper we…

Numerical Analysis · Mathematics 2021-01-01 Daniel Gerth , Ronny Ramlau

State-of-the-art image reconstruction often relies on complex, highly parameterized deep architectures. We propose an alternative: a data-driven reconstruction method inspired by the classic Tikhonov regularization. Our approach iteratively…

Image and Video Processing · Electrical Eng. & Systems 2025-02-07 Mehrsa Pourya , Erich Kobler , Michael Unser , Sebastian Neumayer

Many recent successful (deep) reinforcement learning algorithms make use of regularization, generally based on entropy or Kullback-Leibler divergence. We propose a general theory of regularized Markov Decision Processes that generalizes…

Machine Learning · Computer Science 2019-06-05 Matthieu Geist , Bruno Scherrer , Olivier Pietquin

We consider the monotone inclusion problems in real Hilbert spaces. Proximal splitting algorithms are very popular technique to solve it and generally achieve weak convergence under mild assumptions. Researchers assume the strong conditions…

Optimization and Control · Mathematics 2022-05-05 Avinash Dixit , D. R. Sahu , Pankaj Gautam , T. Som

We study strategies for increasing the precision in the blurring models by maintaining a complexity in the related numerical linear algebra procedures (matrix-vector product, linear system solution, computation of eigenvalues etc.) of the…

Numerical Analysis · Mathematics 2009-06-16 Marco Donatelli

We investigate the modeling and the numerical solution of machine learning problems with prediction functions which are linear combinations of elements of a possibly infinite-dimensional dictionary. We propose a novel flexible composite…

Statistics Theory · Mathematics 2015-12-03 Patrick L. Combettes , Saverio Salzo , Silvia Villa

A central challenge in continual learning is forgetting, the loss of performance on previously learned tasks induced by sequential adaptation to new ones. While forgetting has been extensively studied empirically, rigorous theoretical…

Machine Learning · Computer Science 2026-04-16 Zonghuan Xu , Xingjun Ma

We investigate the regularizing behavior of an iterative Krylov subspace method for the solution of linear inverse problems in precisions lower than double. Recent works have considered the projection of iterated Tikhonov methods using…

Numerical Analysis · Mathematics 2025-12-02 Chelsea Drum , James. G. Nagy , Lucas Onisk

We propose a novel dictionary learning add-on for existing approximation algorithms for spherical inverse problems such as the downward continuation of the gravitational potential. The Inverse Problem Matching Pursuit (IPMP) algorithms…

Numerical Analysis · Mathematics 2022-03-25 Naomi Schneider , Volker Michel

We study generalization properties of kernel regularized least squares regression based on a partitioning approach. We show that optimal rates of convergence are preserved if the number of local sets grows sufficiently slowly with the…

Statistics Theory · Mathematics 2019-02-26 Nicole Mücke

In this work, we revisit Transformer optimization through the lens of second-order geometry and establish a direct connection between architectural design, activation scale, the Hessian matrix, and the maximum tolerable learning rate. We…

Machine Learning · Computer Science 2026-02-03 Marco Chen , Xianbiao Qi , Yelin He , Jiaquan Ye , Rong Xiao

In recent years, functional linear models have attracted growing attention in statistics and machine learning, with the aim of recovering the slope function or its functional predictor. This paper considers online regularized learning…

Machine Learning · Statistics 2022-11-28 Yuan Mao , Zheng-Chu Guo