English
Related papers

Related papers: Newton method for $\ell_0$-regularized optimizatio…

200 papers

The non-convex $\alpha\|\cdot\|_{\ell_1}-\beta\| \cdot\|_{\ell_2}$ $(\alpha\ge\beta\geq0)$ regularization has attracted attention in the field of sparse recovery. One way to obtain a minimizer of this regularization is the…

Numerical Analysis · Mathematics 2020-12-30 Liang Ding , Weimin Han

We consider the problem of training a deep neural network with nonsmooth regularization to retrieve a sparse and efficient sub-structure. Our regularizer is only assumed to be lower semi-continuous and prox-bounded. We combine an adaptive…

Machine Learning · Statistics 2022-06-20 Dounia Lakhmiri , Dominique Orban , Andrea Lodi

We consider solving equality-constrained nonlinear, nonconvex optimization problems. This class of problems appears widely in a variety of applications in machine learning and engineering, ranging from constrained deep neural networks, to…

Optimization and Control · Mathematics 2023-05-31 Ilgee Hong , Sen Na , Michael W. Mahoney , Mladen Kolar

Thresholding algorithms for sparse optimization problems involve two key components: search directions and thresholding strategies. In this paper, we use the compressed Newton direction as a search direction, derived by confining the…

Information Theory · Computer Science 2025-10-07 Nan Meng , Yun-Bin Zhao

We consider a class of learning problems that involve a structured sparsity-inducing norm defined as the sum of $\ell_\infty$-norms over groups of variables. Whereas a lot of effort has been put in developing fast optimization methods when…

Machine Learning · Computer Science 2010-09-02 Julien Mairal , Rodolphe Jenatton , Guillaume Obozinski , Francis Bach

In [19], a general, inexact, efficient proximal quasi-Newton algorithm for composite optimization problems has been proposed and a sublinear global convergence rate has been established. In this paper, we analyze the convergence properties…

Numerical Analysis · Computer Science 2017-10-18 Hiva Ghanbari , Katya Scheinberg

In modern machine learning, attention computation is a fundamental task for training large language models such as Transformer, GPT-4 and ChatGPT. In this work, we study exponential regression problem which is inspired by the softmax/exp…

Machine Learning · Computer Science 2023-05-12 Zhihang Li , Zhao Song , Tianyi Zhou

Recently, finding the sparsest solution of an underdetermined linear system has become an important request in many areas such as compressed sensing, image processing, statistical learning, and data sparse approximation. In this paper, we…

Optimization and Control · Mathematics 2020-03-31 Jialiang Xu

Convex regularizers are often used for sparse learning. They are easy to optimize, but can lead to inferior prediction performance. The difference of $\ell_1$ and $\ell_2$ ($\ell_{1-2}$) regularizer has been recently proposed as a nonconvex…

Machine Learning · Computer Science 2017-06-21 Quanming Yao , James T. Kwok , Xiawei Guo

Neural network pruning is a key technique towards engineering large yet scalable, interpretable, and generalizable models. Prior work on the subject has developed largely along two orthogonal directions: (1) differentiable pruning for…

Machine Learning · Computer Science 2025-02-12 Taisuke Yasuda , Kyriakos Axiotis , Gang Fu , MohammadHossein Bateni , Vahab Mirrokni

We present a Newton-type method that converges fast from any initialization and for arbitrary convex objectives with Lipschitz Hessians. We achieve this by merging the ideas of cubic regularization with a certain adaptive…

Optimization and Control · Mathematics 2023-03-02 Konstantin Mishchenko

A convergence analysis is developed for the regularized Newton method for training neural networks (NNs) in the overparameterized limit. As the number of hidden units tends to infinity, the NN training dynamics converge in probability to…

Machine Learning · Computer Science 2026-05-21 Konstantin Riedl , Konstantinos Spiliopoulos , Justin Sirignano

Sparse recovery is ubiquitous in machine learning and signal processing. Due to the NP-hard nature of sparse recovery, existing methods are known to suffer either from restrictive (or even unknown) applicability conditions, or high…

Signal Processing · Electrical Eng. & Systems 2024-03-21 William de Vazelhes , Bhaskar Mukhoty , Xiao-Tong Yuan , Bin Gu

We propose and analyze a perturbative regularization method to approximate quadratic optimization problems with finite-dimensional degeneracy. The original problem is first approximated by a regularized problem depending on a small positive…

Numerical Analysis · Mathematics 2026-03-16 C. G. Gebhardt , I. Romero

Data augmentation is one of the most popular techniques for improving the robustness of neural networks. In addition to directly training the model with original samples and augmented samples, a torrent of methods regularizing the distance…

Machine Learning · Computer Science 2020-11-30 Haohan Wang , Zeyi Huang , Xindi Wu , Eric P. Xing

Motivated by re-weighted $\ell_1$ approaches for sparse recovery, we propose a lifted $\ell_1$ (LL1) regularization which is a generalized form of several popular regularizations in the literature. By exploring such connections, we discover…

Signal Processing · Electrical Eng. & Systems 2022-05-13 Yaghoub Rahimi , Sung Ha Kang , Yifei Lou

In this work we propose and analyze a novel approach for group sparse recovery. It is based on regularized least squares with an $\ell^0(\ell^2)$ penalty, which penalizes the number of nonzero groups. One distinct feature of the approach is…

Information Theory · Computer Science 2016-12-21 Yuling Jiao , Bangti Jin , Xiliang Lu

Newton's method is the most widespread high-order method, demanding the gradient and the Hessian of the objective function. However, one of the main disadvantages of Newtons method is its lack of global convergence and high iteration cost.…

This paper aims at developing two versions of the generalized Newton method to compute not merely arbitrary local minimizers of nonsmooth optimization problems but just those, which possess an important stability property known as tilt…

Optimization and Control · Mathematics 2021-01-01 Boris Mordukhovich , Ebrahim Sarabi

We develop an approach to risk minimization and stochastic optimization that provides a convex surrogate for variance, allowing near-optimal and computationally efficient trading between approximation and estimation error. Our approach…

Machine Learning · Statistics 2017-12-15 John Duchi , Hongseok Namkoong