English
Related papers

Related papers: A Majorization-Minimization Gauss-Newton Method fo…

200 papers

Following early work on Hessian-free methods for deep learning, we study a stochastic generalized Gauss-Newton method (SGN) for training DNNs. SGN is a second-order optimization method, with efficient iterations, that we demonstrate to…

Machine Learning · Computer Science 2020-06-11 Matilde Gargiani , Andrea Zanelli , Moritz Diehl , Frank Hutter

We extend the well-known BFGS quasi-Newton method and its memory-limited variant LBFGS to the optimization of nonsmooth convex objectives. This is done in a rigorous fashion by generalizing three components of BFGS to subdifferentials: the…

Machine Learning · Statistics 2010-11-30 Jin Yu , S. V. N. Vishwanathan , Simon Guenter , Nicol N. Schraudolph

This paper presents and analyzes the first matrix optimization model which allows general coordinate and spectral constraints. The breadth of problems our model covers is exemplified by a lengthy list of examples from the literature,…

Optimization and Control · Mathematics 2024-10-15 Casey Garner , Gilad Lerman , Shuzhong Zhang

In a widely-studied class of multi-parametric optimization problems, the objective value of each solution is an affine function of real-valued parameters. Then, the goal is to provide an optimal solution set, i.e., a set containing an…

Optimization and Control · Mathematics 2021-12-14 Stephan Helfrich , Arne Herzel , Stefan Ruzika , Clemens Thielen

Low-rank matrix factorization (MF) is an important technique in data science. The key idea of MF is that there exists latent structures in the data, by uncovering which we could obtain a compressed representation of the data. By factorizing…

Numerical Analysis · Computer Science 2016-05-09 Yuan Lu , Jie Yang

Training 1-bit deep convolutional neural networks (DCNNs) is one of the most challenging problems in computer vision, because it is much easier to get trapped into local minima than conventional DCNNs. The reason lies in that the binarized…

Computer Vision and Pattern Recognition · Computer Science 2020-02-03 Chunlei Liu , Wenrui Ding , Yuan Hu , Baochang Zhang , Jianzhuang Liu , Guodong Guo

It is the main goal of this paper to propose a novel method to perform matrix completion on-line. Motivated by a wide variety of applications, ranging from the design of recommender systems to sensor network localization through seismic…

Machine Learning · Statistics 2014-01-13 Charanpal Dhanjal , Romaric Gaudel , Stéphan Clémençon

We consider the problem of matrix completion with graphs as side information depicting the interrelations between variables. The key challenge lies in leveraging the similarity structure of the graph to enhance matrix recovery. Existing…

Machine Learning · Computer Science 2025-02-13 Yao Wang , Yiyang Yang , Kaidong Wang , Shanxing Gao , Xiuwu Liao

Deep learning algorithms often require solving a highly non-linear and nonconvex unconstrained optimization problem. Methods for solving optimization problems in large-scale machine learning, such as deep learning and deep reinforcement…

Machine Learning · Computer Science 2019-09-06 Jacob Rafati , Roummel F. Marcia

The majority of parameters in neural networks are naturally represented as matrices. However, most commonly used optimizers treat these matrix parameters as flattened vectors during optimization, potentially overlooking their inherent…

Machine Learning · Statistics 2026-04-15 Wei Shen , Ruichuan Huang , Minhui Huang , Cong Shen , Jiawei Zhang

The majorization-minimization (MM) principle is an extremely general framework for deriving optimization algorithms. It includes the expectation-maximization (EM) algorithm, proximal gradient algorithm, concave-convex procedure, quadratic…

Optimization and Control · Mathematics 2021-06-08 Kenneth Lange , Joong-Ho Won , Alfonso Landeros , Hua Zhou

In this paper, we propose a new algorithm for recovery of low-rank matrices from compressed linear measurements. The underlying idea of this algorithm is to closely approximate the rank function with a smooth function of singular values,…

Information Theory · Computer Science 2016-11-18 Mohammadreza Malek-Mohammadi , Massoud Babaie-Zadeh , Mikael Skoglund

Matrix completion aims to reconstruct a data matrix based on observations of a small number of its entries. Usually in matrix completion a single matrix is considered, which can be, for example, a rating matrix in recommendation system.…

Machine Learning · Statistics 2019-10-22 Mokhtar Z. Alaya , Olga Klopp

The modified Gram-Schmidt (MGS) orthogonalization is one of the most well-used algorithms for computing the thin QR factorization. MGS can be straightforwardly extended to a non-standard inner product with respect to a symmetric positive…

Numerical Analysis · Mathematics 2017-03-31 Akira Imakura , Yusaku Yamamoto

In signal processing and data recovery, reconstructing a signal from quadratic measurements poses a significant challenge, particularly in high-dimensional settings where measurements $m$ is far less than the signal dimension $n$ (i.e., $m…

Information Theory · Computer Science 2025-07-11 Jinming Wen , Yi Hu , Meng Huang

The problem of low-rank matrix completion has recently generated a lot of interest leading to several results that offer exact solutions to the problem. However, in order to do so, these methods make assumptions that can be quite…

Machine Learning · Statistics 2014-07-14 Srinadh Bhojanapalli , Prateek Jain

We propose a computational framework for computing low-rank approximations to the ensemble of solutions of a parametrized system of the form $A(\xi)x(\xi)+g(x(\xi))=b(\xi)$ for multiple parameter values. The central idea is to reinterpret…

Numerical Analysis · Mathematics 2026-04-09 Marco Sutti , Tommaso Vanzan

The nonconvex formulation of the matrix completion problem has received significant attention in recent years due to its affordable complexity compared to the convex formulation. Gradient Descent (GD) is a simple yet efficient baseline…

Machine Learning · Statistics 2025-07-03 Daesung Kim , Hye Won Chung

In 1-bit compressive sensing, each measurement is quantized to a single bit, namely the sign of a linear function of an unknown vector, and the goal is to accurately recover the vector. While it is most popular to assume a standard Gaussian…

Machine Learning · Computer Science 2021-08-10 Zhaoqiang Liu , Subhroshekhar Ghosh , Jun Han , Jonathan Scarlett

In this article, we introduce a novel normalization technique for neural network weight matrices, which we term weight conditioning. This approach aims to narrow the gap between the smallest and largest singular values of the weight…

Computer Vision and Pattern Recognition · Computer Science 2026-03-16 Hemanth Saratchandran , Thomas X. Wang , Simon Lucey