English
Related papers

Related papers: Algorithmic Regularization in Over-parameterized M…

200 papers

This paper introduces an iterative algorithm for training nonparametric additive models that enjoys favorable memory storage and computational requirements. The algorithm can be viewed as the functional counterpart of stochastic gradient…

Machine Learning · Statistics 2026-01-01 Xin Chen , Jason M. Klusowski

Classical optimisation theory guarantees monotonic objective decrease for gradient descent (GD) when employed in a small step size, or ``stable", regime. In contrast, gradient descent on neural networks is frequently performed in a large…

Machine Learning · Computer Science 2025-10-21 Lachlan Ewen MacDonald , Hancheng Min , Leandro Palma , Salma Tarmoun , Ziqing Xu , René Vidal

This paper studies the stability of low-rank implicit regularization in perturbed deep matrix factorization, where the target matrix is corrupted by a noise matrix. We first derive sufficient spectral conditions under which gradient descent…

Optimization and Control · Mathematics 2026-05-28 Jingzhe Wang , Hung-Hsu Chou

Double descent refers to the phase transition that is exhibited by the generalization error of unregularized learning models when varying the ratio between the number of parameters and the number of training samples. The recent success of…

Machine Learning · Computer Science 2020-06-19 Michał Dereziński , Feynman Liang , Michael W. Mahoney

The problem of solving partial differential equations (PDEs) can be formulated into a least-squares minimization problem, where neural networks are used to parametrize PDE solutions. A global minimizer corresponds to a neural network that…

Numerical Analysis · Mathematics 2020-12-14 Tao Luo , Haizhao Yang

Most existing methodologies of estimating low-rank matrices rely on Burer-Monteiro factorization, but these approaches can suffer from slow convergence, especially when dealing with solutions characterized by a large condition number,…

Optimization and Control · Mathematics 2024-03-06 Teng Zhang , Xing Fan

We study the problem of training deep neural networks with Rectified Linear Unit (ReLU) activation function using gradient descent and stochastic gradient descent. In particular, we study the binary classification problem and show that for…

Machine Learning · Computer Science 2018-12-31 Difan Zou , Yuan Cao , Dongruo Zhou , Quanquan Gu

Natural gradient descent (NGD) is a powerful optimization technique for machine learning, but the computational complexity of the inverse Fisher information matrix limits its application in training deep neural networks. To overcome this…

Machine Learning · Computer Science 2024-12-11 Weihua Liu , Said Boumaraf , Jianwu Li , Chaochao Lin , Xiabi Liu , Lijuan Niu , Naoufel Werghi

Neural networks are widely used to approximate unknown functions in control. A common neural network architecture uses a single hidden layer (i.e. a shallow network), in which the input parameters are fixed in advance and only the output…

Machine Learning · Computer Science 2024-10-08 Andrew Lamperski , Siddharth Salapaka

As the problem of minimizing functionals on the Wasserstein space encompasses many applications in machine learning, different optimization algorithms on $\mathbb{R}^d$ have received their counterpart analog on the Wasserstein space. We…

Optimization and Control · Mathematics 2024-11-20 Clément Bonet , Théo Uscidda , Adam David , Pierre-Cyril Aubin-Frankowski , Anna Korba

The advancements in neural rendering have increased the need for techniques that enable intuitive editing of 3D objects represented as neural implicit surfaces. This paper introduces a novel neural algorithm for parameterizing neural…

Computer Vision and Pattern Recognition · Computer Science 2024-07-16 Baixin Xu , Jiangbei Hu , Fei Hou , Kwan-Yee Lin , Wayne Wu , Chen Qian , Ying He

We propose an inexact optimization algorithm on Riemannian manifolds, motivated by quadratic discrimination tasks in high-dimensional, low-sample-size (HDLSS) imaging settings. In such applications, gradient evaluations are often biased due…

Optimization and Control · Mathematics 2025-07-08 Uday Talwar , Meredith K. Kupinski , Afrooz Jalilzadeh

Deep neural networks (DNNs) have demonstrated dominating performance in many fields; since AlexNet, networks used in practice are going wider and deeper. On the theoretical side, a long line of works has been focusing on training neural…

Machine Learning · Computer Science 2019-06-18 Zeyuan Allen-Zhu , Yuanzhi Li , Zhao Song

While deep learning is successful in a number of applications, it is not yet well understood theoretically. A satisfactory theoretical characterization of deep learning however, is beginning to emerge. It covers the following questions: 1)…

Machine Learning · Computer Science 2019-08-27 Tomaso Poggio , Andrzej Banburski , Qianli Liao

Gradient descent dynamics on the deep matrix factorization problem is extensively studied as a simplified theoretical model for deep neural networks. Although the convergence theory for two-layer matrix factorization is well-established, no…

Optimization and Control · Mathematics 2025-11-20 Minrui Luo , Weihang Xu , Xiang Gao , Maryam Fazel , Simon Shaolei Du

In this paper, we theoretically prove that gradient descent can find a global minimum of non-convex optimization of all layers for nonlinear deep neural networks of sizes commonly encountered in practice. The theory developed in this paper…

Machine Learning · Statistics 2020-06-18 Kenji Kawaguchi , Jiaoyang Huang

In this work, we study the iteration complexity of gradient methods for minimizing convex quadratic functions regularized by powers of Euclidean norms. We show that, due to the uniform convexity of the objective, gradient methods have…

Optimization and Control · Mathematics 2025-01-28 Daniel Berg Thomsen , Nikita Doikov

We describe novel subgradient methods for a broad class of matrix optimization problems involving nuclear norm regularization. Unlike existing approaches, our method executes very cheap iterations by combining low-rank stochastic…

Machine Learning · Computer Science 2012-07-03 Haim Avron , Satyen Kale , Shiva Kasiviswanathan , Vikas Sindhwani

Stochastic gradient descent (SGD) on a low-rank factorization is commonly employed to speed up matrix problems including matrix completion, subspace tracking, and SDP relaxation. In this paper, we exhibit a step size scheme for SGD on a…

Machine Learning · Computer Science 2015-02-11 Christopher De Sa , Kunle Olukotun , Christopher Ré

In high-dimensional and/or non-parametric regression problems, regularization (or penalization) is used to control model complexity and induce desired structure. Each penalty has a weight parameter that indicates how strongly the structure…

Machine Learning · Statistics 2017-03-30 Jean Feng , Noah Simon