English
Related papers

Related papers: Implicit Regularization of Bregman Proximal Point …

200 papers

The paper introduces scaled Bregman distances of probability distributions which admit non-uniform contributions of observed events. They are introduced in a general form covering not only the distances of discrete and continuous stochastic…

Information Theory · Computer Science 2021-05-12 Wolfgang Stummer , Igor Vajda

Many applications using large datasets require efficient methods for minimizing a proximable convex function subject to satisfying a set of linear constraints within a specified tolerance. For this task, we present a proximal projection…

Optimization and Control · Mathematics 2024-12-10 Howard Heaton

A standard model for image reconstruction involves the minimization of a data-fidelity term along with a regularizer, where the optimization is performed using proximal algorithms such as ISTA and ADMM. In plug-and-play (PnP)…

Optimization and Control · Mathematics 2021-04-22 Pravin Nair , Ruturaj G. Gavaskar , Kunal N. Chaudhury

How to extract more and useful information for single image super resolution is an imperative and difficult problem. Learning-based method is a representative method for such task. However, the results are not so stable as there may exist…

Image and Video Processing · Electrical Eng. & Systems 2020-03-25 Hu Liang , Shengrong Zhao

For the inclusion problem involving two maximal monotone operators, under the metric subregularity of the composite operator, we derive the linear convergence of the generalized proximal point algorithm and several splitting algorithms,…

Optimization and Control · Mathematics 2016-09-28 Li Shen , Shaohua Pan

In this work, we investigate the margin-maximization bias exhibited by gradient-based algorithms in classifying linearly separable data. We present an in-depth analysis of the specific properties of the velocity field associated with…

Machine Learning · Computer Science 2024-12-30 Mingze Wang , Zeping Min , Lei Wu

The approximate joint diagonalization of a set of matrices consists in finding a basis in which these matrices are as diagonal as possible. This problem naturally appears in several statistical learning tasks such as blind signal…

Numerical Analysis · Computer Science 2018-12-03 Pierre Ablin , Jean-François Cardoso , Alexandre Gramfort

We develop a Bregman proximal gradient method for structure learning on linear structural causal models. While the problem is non-convex, has high curvature and is in fact NP-hard, Bregman gradient methods allow us to neutralize at least…

Machine Learning · Statistics 2020-11-06 Manon Romain , Alexandre d'Aspremont

The proximal point algorithm (PPA) is the most widely recognized method for solving inclusion problems and serves as the foundation for many numerical algorithms. Despite this popularity, its convergence results have been largely limited to…

Optimization and Control · Mathematics 2024-05-07 Brecht Evens , Pieter Pas , Puya Latafat , Panagiotis Patrinos

Minimization of suitable statistical distances~(between the data and model densities) has proved to be a very useful technique in the field of robust inference. Apart from the class of $\phi$-divergences of \cite{a} and \cite{b}, the…

Statistics Theory · Mathematics 2021-01-25 Sancharee Basak , Ayanendranath Basu

We study deterministic and stochastic primal-dual sub-gradient algorithms for distributed optimization of a separable objective function with global inequality constraints. In both algorithms, the norm of the Lagrangian multipliers are…

Optimization and Control · Mathematics 2017-06-20 Masoud Badiei Khuzani , Na Li

We provide a statistical analysis of regularization-based continual learning on a sequence of linear regression tasks, with emphasis on how different regularization terms affect the model performance. We first derive the convergence rate…

Machine Learning · Computer Science 2024-06-11 Xuyang Zhao , Huiyuan Wang , Weiran Huang , Wei Lin

We unify f-divergences, Bregman divergences, surrogate loss bounds (regret bounds), proper scoring rules, matching losses, cost curves, ROC-curves and information. We do this by systematically studying integral and variational…

Machine Learning · Statistics 2009-01-06 Mark D. Reid , Robert C. Williamson

Recent work by Woodworth et al. (2020) shows that the optimization dynamics of gradient descent for overparameterized problems can be viewed as low-dimensional dual dynamics induced by a mirror map, explaining the implicit regularization…

Machine Learning · Computer Science 2024-10-21 Shuyang Wang , Diego Klabjan

The linearly constrained matrix rank minimization problem is widely applicable in many fields such as control, signal processing and system identification. The tightest convex relaxation of this problem is the linearly constrained nuclear…

Optimization and Control · Mathematics 2009-05-12 Shiqian Ma , Donald Goldfarb , Lifeng Chen

This paper introduces a novel approach for learning to rank (LETOR) based on the notion of monotone retargeting. It involves minimizing a divergence between all monotonic increasing transformations of the training scores and a parameterized…

Machine Learning · Computer Science 2012-10-19 Sreangsu Acharyya , Oluwasanmi Koyejo , Joydeep Ghosh

In this paper, we present a new policy gradient (PG) methods, namely the block policy mirror descent (BPMD) method for solving a class of regularized reinforcement learning (RL) problems with (strongly)-convex regularizers. Compared to the…

Machine Learning · Computer Science 2022-09-20 Guanghui Lan , Yan Li , Tuo Zhao

Moreau's seminal paper, introducing what is now called the Moreau envelope and the proximity operator (also known as the proximal mapping), appeared in 1965. The Moreau envelope of a given convex function provides a regularized version…

Functional Analysis · Mathematics 2020-04-14 Heinz H. Bauschke , Minh N. Dao , Scott B. Lindstrom

Increasing utilization of machine learning based decision support systems emphasizes the need for resulting predictions to be both accurate and fair to all stakeholders. In this work we present a novel approach to increase a Neural Network…

Machine Learning · Computer Science 2021-11-08 Bhanu Jain , Manfred Huber , Ramez Elmasri

It has been reported repeatedly that discriminative learning of distance metric boosts the pattern recognition performance. A weak point of ITML-based methods is that the distance threshold for similarity/dissimilarity constraints must be…

Machine Learning · Computer Science 2018-02-14 Yuya Onuma , Rachelle Rivero , Tsuyoshi Kato