English
Related papers

Related papers: Preconditioning via Diagonal Scaling

200 papers

Stochastic gradient-based descent (SGD), have long been central to training large language models (LLMs). However, their effectiveness is increasingly being questioned, particularly in large-scale applications where empirical evidence…

Machine Learning · Computer Science 2025-07-03 Di Zhang , Yihang Zhang

We explore a scaled spectral preconditioner for the efficient solution of sequences of symmetric and positive-definite linear systems. We design the scaled preconditioner not only as an approximation of the inverse of the linear system but…

Numerical Analysis · Mathematics 2024-10-04 Youssef Diouane , Selime Gürol , Oussama Mouhtal , Dominique Orban

We propose a first-order method for solving inequality constrained optimization problems. The method is derived from our previous work [12], a modified search direction method (MSDM) that applies the singular-value decomposition of…

Optimization and Control · Mathematics 2020-03-12 Long Chen , Wenyi Chen , Kai-Uwe Bletzinger

We study Stochastic Gradient Descent with AdaGrad stepsizes: a popular adaptive (self-tuning) method for first-order stochastic optimization. Despite being well studied, existing analyses of this method suffer from various shortcomings:…

Machine Learning · Computer Science 2023-06-13 Amit Attia , Tomer Koren

In this paper, we propose and analyze an inexact version of the symmetric proximal alternating direction method of multipliers (ADMM) for solving linearly constrained optimization problems. Basically, the method allows its first subproblem…

Optimization and Control · Mathematics 2020-06-05 Vando A. Adona , Max L. N. Gonçalves

In this paper, we study a general optimization model, which covers a large class of existing models for many applications in imaging sciences. To solve the resulting possibly nonconvex, nonsmooth and non-Lipschitz optimization problem, we…

Optimization and Control · Mathematics 2016-09-30 Lei Yang , Ting Kei Pong , Xiaojun Chen

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

The reduction of computational costs in the numerical solution of nonstationary problems is achieved through splitting schemes. In this case, solving a set of less computationally complex problems provides the transition to a new level in…

Numerical Analysis · Mathematics 2022-10-26 Petr N. Vabishchevich

Stochastic Gradient Descent (SGD) methods see many uses in optimization problems. Modifications to the algorithm, such as momentum-based SGD methods have been known to produce better results in certain cases. Much of this, however, is due…

Machine Learning · Computer Science 2025-04-22 Eric Lu

The operation of large-scale infrastructure networks requires scalable optimization schemes. To guarantee safe system operation, a high degree of feasibility in a small number of iterations is important. Decomposition schemes can help to…

Systems and Control · Electrical Eng. & Systems 2024-12-02 Alexander Engelmann , Sungho Shin , François Pacaud , Victor M. Zavala

Low-rank matrix estimation is a canonical problem that finds numerous applications in signal processing, machine learning and imaging science. A popular approach in practice is to factorize the matrix into two compact low-rank factors, and…

Machine Learning · Computer Science 2021-06-16 Tian Tong , Cong Ma , Yuejie Chi

A framework is introduced for sequentially solving convex stochastic minimization problems, where the objective functions change slowly, in the sense that the distance between successive minimizers is bounded. The minimization problems are…

Optimization and Control · Mathematics 2018-03-12 Craig Wilson , Venugopal Veeravalli , Angelia Nedich

Adaptive gradient methods, which adopt historical gradient information to automatically adjust the learning rate, despite the nice property of fast convergence, have been observed to generalize worse than stochastic gradient descent (SGD)…

Machine Learning · Computer Science 2020-06-24 Jinghui Chen , Dongruo Zhou , Yiqi Tang , Ziyan Yang , Yuan Cao , Quanquan Gu

We present a novel preconditioning technique for proximal optimization methods that relies on graph algorithms to construct effective preconditioners. Such combinatorial preconditioners arise from partitioning the graph into forests. We…

Optimization and Control · Mathematics 2018-02-22 Thomas Möllenhoff , Zhenzhang Ye , Tao Wu , Daniel Cremers

Employing the ideas of non-linear preconditioning and testing of the classical proximal point method, we formalise common arguments in convergence rate and convergence proofs of optimisation methods to the verification of a simple…

Optimization and Control · Mathematics 2020-10-06 Tuomo Valkonen

In this paper we propose an efficient distributed algorithm for solving loosely coupled convex optimization problems. The algorithm is based on a primal-dual interior-point method in which we use the alternating direction method of…

Optimization and Control · Mathematics 2015-02-10 Mariette Annergren , Sina Khoshfetrat Pakazad , Anders Hansson , Bo Wahlberg

Gaussian process hyperparameter optimization requires linear solves with, and log-determinants of, large kernel matrices. Iterative numerical techniques are becoming popular to scale to larger datasets, relying on the conjugate gradient…

Machine Learning · Computer Science 2022-06-22 Jonathan Wenger , Geoff Pleiss , Philipp Hennig , John P. Cunningham , Jacob R. Gardner

The article discusses distributed gradient-descent algorithms for computing local and global minima in nonconvex optimization. For local optimization, we focus on distributed stochastic gradient descent (D-SGD)--a simple network-based…

Optimization and Control · Mathematics 2020-09-17 Brian Swenson , Soummya Kar , H. Vincent Poor , José M. F. Moura , Aaron Jaech

In this article, we propose and study a stochastic and relaxed preconditioned Douglas--Rachford splitting method to solve saddle-point problems that have separable dual variables. We prove the almost sure convergence of the iteration…

Optimization and Control · Mathematics 2024-10-01 Yakun Dong , Kristian Bredies , Hongpeng Sun

Stochastic Gradient Langevin Dynamics infuses isotropic gradient noise to SGD to help navigate pathological curvature in the loss landscape for deep networks. Isotropic nature of the noise leads to poor scaling, and adaptive methods based…

Machine Learning · Computer Science 2019-06-13 Chandrasekaran Anirudh Bhardwaj