English
Related papers

Related papers: Preconditioned Gradient Descent for Over-Parameter…

200 papers

We consider minimizing a twice-differentiable, $L$-smooth, and $\mu$-strongly convex objective $\phi$ over an $n\times n$ positive semidefinite matrix $M\succeq0$, under the assumption that the minimizer $M^{\star}$ has low rank…

Optimization and Control · Mathematics 2025-02-04 Richard Y. Zhang

A variant of consensus based distributed gradient descent (\textbf{DGD}) is studied for finite sums of smooth but possibly non-convex functions. In particular, the local gradient term in the fixed step-size iteration of each agent is…

Optimization and Control · Mathematics 2026-05-27 Lei Qin , Michael Cantoni , Ye Pu

In the context of deep learning, many optimization methods use gradient covariance information in order to accelerate the convergence of Stochastic Gradient Descent. In particular, starting with Adagrad, a seemingly endless line of research…

Machine Learning · Computer Science 2020-12-08 Nikolaos Tselepidis , Jonas Kohler , Antonio Orvieto

Over-parametrization is an important technique in training neural networks. In both theory and practice, training a larger network allows the optimization algorithm to avoid bad local optimal solutions. In this paper we study a closely…

Machine Learning · Statistics 2020-10-23 Xiang Wang , Chenwei Wu , Jason D. Lee , Tengyu Ma , Rong Ge

It has been observed in a variety of contexts that gradient descent methods have great success in solving low-rank matrix factorization problems, despite the relevant problem formulation being non-convex. We tackle a particular instance of…

Numerical Analysis · Computer Science 2016-06-28 Dejiao Zhang , Laura Balzano

The sparsity constrained rank-one matrix approximation problem is a difficult mathematical optimization problem which arises in a wide array of useful applications in engineering, machine learning and statistics, and the design of…

Optimization and Control · Mathematics 2012-06-27 Ronny Luss , Marc Teboulle

Stochastic Gradient Decent (SGD) is one of the core techniques behind the success of deep neural networks. The gradient provides information on the direction in which a function has the steepest rate of change. The main problem with basic…

The conditions of relative smoothness and relative strong convexity were recently introduced for the analysis of Bregman gradient methods for convex optimization. We introduce a generalized left-preconditioning method for gradient descent,…

Optimization and Control · Mathematics 2020-12-09 Chris J. Maddison , Daniel Paulin , Yee Whye Teh , Arnaud Doucet

This paper presents a novel algorithm that leverages Stochastic Gradient Descent strategies in conjunction with Random Features to augment the scalability of Conic Particle Gradient Descent (CPGD) specifically tailored for solving sparse…

Optimization and Control · Mathematics 2025-09-05 Yohann De Castro , Sébastien Gadat , Clément Marteau

We consider the minimization problem with the truncated quadratic regularization with gradient operator, which is a nonsmooth and nonconvex problem. We cooperated the classical preconditioned iterations for linear equations into the…

Optimization and Control · Mathematics 2021-05-04 Shengxiang Deng , Hongpeng Sun

Latent variable models are powerful tools for modeling complex phenomena involving in particular partially observed data, unobserved variables or underlying complex unknown structures. Inference is often difficult due to the latent…

Statistics Theory · Mathematics 2023-06-23 Charlotte Baey , Maud Delattre , Estelle Kuhn , Jean-Benoist Leger , Sarah Lemler

Low rank approximation is a commonly occurring problem in many computer vision and machine learning applications. There are two common ways of optimizing the resulting models. Either the set of matrices with a given rank can be explicitly…

Computer Vision and Pattern Recognition · Computer Science 2019-07-24 Marcus Valtonen Örnhag , Carl Olsson , Anders Heyden

We consider the problem of minimizing a convex function over a closed convex set, with Projected Gradient Descent (PGD). We propose a fully parameter-free version of AdaGrad, which is adaptive to the distance between the initialization and…

Machine Learning · Statistics 2023-06-01 Evgenii Chzhen , Christophe Giraud , Gilles Stoltz

Tensor decompositions, which represent an $N$-order tensor using approximately $N$ factors of much smaller dimensions, can significantly reduce the number of parameters. This is particularly beneficial for high-order tensors, as the number…

Machine Learning · Computer Science 2025-06-23 Zhen Qin , Michael B. Wakin , Zhihui Zhu

Natural gradient descent has proven effective at mitigating the effects of pathological curvature in neural network optimization, but little is known theoretically about its convergence properties, especially for \emph{nonlinear} networks.…

Machine Learning · Statistics 2019-10-29 Guodong Zhang , James Martens , Roger Grosse

The alternating gradient descent (AGD) is a simple but popular algorithm which has been applied to problems in optimization, machine learning, data ming, and signal processing, etc. The algorithm updates two blocks of variables in an…

Optimization and Control · Mathematics 2018-03-01 Songtao Lu , Mingyi Hong , Zhengdao Wang

Communication has been seen as a significant bottleneck in industrial applications over large-scale networks. To alleviate the communication burden, sign-based optimization algorithms have gained popularity recently in both industrial and…

Optimization and Control · Mathematics 2021-09-07 Xiuxian Li , Kuo-Yi Lin , Li Li , Yiguang Hong , Jie Chen

In nonsmooth optimization, a negative subgradient is not necessarily a descent direction, making the design of convergent descent methods based on zeroth-order and first-order information a challenging task. The well-studied bundle methods…

Optimization and Control · Mathematics 2025-05-13 Hanyang Li , Ying Cui

Adaptive gradient methods are typically used for training over-parameterized models. To better understand their behaviour, we study a simplistic setting -- smooth, convex losses with models over-parameterized enough to interpolate the data.…

Machine Learning · Computer Science 2021-02-22 Sharan Vaswani , Issam Laradji , Frederik Kunstner , Si Yi Meng , Mark Schmidt , Simon Lacoste-Julien

Regularization is a widely recognized technique in mathematical optimization. It can be used to smooth out objective functions, refine the feasible solution set, or prevent overfitting in machine learning models. Due to its simplicity and…

Optimization and Control · Mathematics 2024-12-31 Filip Nikolovski , Irena Stojkovska , Katerina Hadzi-Velkova Saneva , Zoran Hadzi-Velkov