English
Related papers

Related papers: Efficient Full-Matrix Adaptive Regularization

200 papers

First-order methods with momentum such as Nesterov's fast gradient method are very useful for convex optimization problems, but can exhibit undesirable oscillations yielding slow convergence rates for some applications. An adaptive…

Optimization and Control · Mathematics 2019-06-14 Donghwan Kim , Jeffrey A. Fessler

Adaptive gradient approaches that automatically adjust the learning rate on a per-feature basis have been very popular for training deep networks. This rich class of algorithms includes Adagrad, RMSprop, Adam, and recent extensions. All…

Machine Learning · Computer Science 2019-05-28 Jihun Yun , Aurelie C. Lozano , Eunho Yang

We present an adaptive regularization algorithm that can be effectively applied to the optimization problem in deep learning framework. Our regularization algorithm aims to take into account the fitness of data to the current state of model…

Machine Learning · Computer Science 2019-09-02 Junghee Cho , Junseok Kwon , Byung-Woo Hong

Human beings can quickly adapt to environmental changes by leveraging learning experience. However, adapting deep neural networks to dynamic environments by machine learning algorithms remains a challenge. To better understand this issue,…

Computer Vision and Pattern Recognition · Computer Science 2021-03-24 Shixiang Tang , Peng Su , Dapeng Chen , Wanli Ouyang

Incorporating a deep generative model as the prior distribution in inverse problems has established substantial success in reconstructing images from corrupted observations. Notwithstanding, the existing optimization approaches use gradient…

Machine Learning · Computer Science 2023-01-31 Tianci Liu , Tong Yang , Quan Zhang , Qi Lei

We introduce a novel adaptive Gaussian Process Regression (GPR) methodology for efficient construction of surrogate models for Bayesian inverse problems with expensive forward model evaluations. An adaptive design strategy focuses on…

Numerical Analysis · Mathematics 2024-05-01 Paolo Villani , Jörg Unger , Martin Weiser

Leveraging second-order information about the loss at the scale of deep networks is one of the main lines of approach for improving the performance of current optimizers for deep learning. Yet, existing approaches for accurate full-matrix…

Machine Learning · Computer Science 2024-06-06 Ionut-Vlad Modoranu , Aleksei Kalinov , Eldar Kurtic , Elias Frantar , Dan Alistarh

In this paper, we consider an unconstrained optimization model where the objective is a sum of a large number of possibly nonconvex functions, though overall the objective is assumed to be smooth and convex. Our bid to solving such model…

Optimization and Control · Mathematics 2022-03-15 Xi Chen , Bo Jiang , Tianyi Lin , Shuzhong Zhang

For solving large-scale non-convex problems, we propose inexact variants of trust region and adaptive cubic regularization methods, which, to increase efficiency, incorporate various approximations. In particular, in addition to approximate…

Optimization and Control · Mathematics 2018-02-21 Zhewei Yao , Peng Xu , Farbod Roosta-Khorasani , Michael W. Mahoney

This paper describes a new efficient conjugate subgradient algorithm which minimizes a convex function containing a least squares fidelity term and an absolute value regularization term. This method is successfully applied to the inversion…

Data Analysis, Statistics and Probability · Physics 2015-06-30 Alessandro Mirone , Pierre Paleo

We study the training dynamics of gradient descent in a softmax self-attention layer trained to perform linear regression and show that a simple first-order optimization algorithm can converge to the globally optimal self-attention…

Machine Learning · Computer Science 2026-03-03 Gautam Goel , Mahdi Soltanolkotabi , Peter Bartlett

For some typical and widely used non-convex half-quadratic regularization models and the Ambrosio-Tortorelli approximate Mumford-Shah model, based on the Kurdyka-\L ojasiewicz analysis and the recent nonconvex proximal algorithms, we…

Optimization and Control · Mathematics 2021-07-30 Shengxiang Deng , Ismail Ben Ayed , Hongpeng Sun

In this paper, we propose a unified two-phase scheme to accelerate any high-order regularized tensor approximation approach on the smooth part of a composite convex optimization model. The proposed scheme has the advantage of not needing to…

Optimization and Control · Mathematics 2020-07-06 Bo Jiang , Tianyi Lin , Shuzhong Zhang

We introduce a fully-corrective generalized conditional gradient method for convex minimization problems involving total variation regularization on multidimensional domains. It relies on alternatively updating an active set of subsets of…

Optimization and Control · Mathematics 2025-12-01 Giacomo Cristinelli , José A. Iglesias , Daniel Walter

In this paper, we focus on solving a sequence of linear systems with an identical (or similar) coefficient matrix. For this type of problems, we investigate the subspace correction and deflation methods, which use an auxiliary matrix…

Numerical Analysis · Mathematics 2022-03-17 Takeshi Iwashita , Kota Ikehara , Takeshi Fukaya , Takeshi Mifune

Gradient methods are widely used in optimization problems. In practice, while the smoothness parameter can be estimated utilizing techniques such as backtracking, estimating the strong convexity parameter remains a challenge; moreover, even…

Optimization and Control · Mathematics 2026-02-17 Xiaozhe Hu , Sara Pollock , Zhongqin Xue , Yunrong Zhu

We propose a new randomized optimization method for high-dimensional problems which can be seen as a generalization of coordinate descent to random subspaces. We show that an adaptive sampling strategy for the random subspace significantly…

Optimization and Control · Mathematics 2019-12-19 Jonathan Lacotte , Mert Pilanci , Marco Pavone

Inverse problems are in many cases solved with optimization techniques. When the underlying model is linear, first-order gradient methods are usually sufficient. With nonlinear models, due to nonconvexity, one must often resort to…

Numerical Analysis · Mathematics 2023-05-15 Arttu Arjas , Mikko J. Sillanpää , Andreas Hauptmann

A novel approach is given to overcome the computational challenges of the full-matrix Adaptive Gradient algorithm (Full AdaGrad) in stochastic optimization. By developing a recursive method that estimates the inverse of the square root of…

Statistics Theory · Mathematics 2025-02-28 Antoine Godichon-Baggioni , Wei Lu , Bruno Portier

We study the problem of recovery of matrices that are simultaneously low rank and row and/or column sparse. Such matrices appear in recent applications in cognitive neuroscience, imaging, computer vision, macroeconomics, and genetics. We…

Machine Learning · Statistics 2019-04-11 Ming Yu , Varun Gupta , Mladen Kolar