English
Related papers

Related papers: Dual Space Preconditioning for Gradient Descent in…

200 papers

Recent years have seen a flurry of activities in designing provably efficient nonconvex procedures for solving statistical estimation problems. Due to the highly nonconvex nature of the empirical loss, state-of-the-art procedures often…

Machine Learning · Computer Science 2020-06-09 Cong Ma , Kaizheng Wang , Yuejie Chi , Yuxin Chen

In this paper we consider a class of optimization problems with a strongly convex objective function and the feasible set given by an intersection of a simple convex set with a set given by a number of linear equality and inequality…

Optimization and Control · Mathematics 2016-05-11 Alexey Chernov , Pavel Dvurechensky , Alexander Gasnikov

When samples have internal structure, we often see a mismatch between the objective optimized during training and the model's goal during inference. For example, in sequence-to-sequence modeling we are interested in high-quality translated…

Machine Learning · Computer Science 2020-10-05 Xi Gao , Han Zhang , Aliakbar Panahi , Tom Arodz

The (gradient-based) bilevel programming framework is widely used in hyperparameter optimization and has achieved excellent performance empirically. Previous theoretical work mainly focuses on its optimization properties, while leaving the…

Machine Learning · Computer Science 2021-10-26 Fan Bao , Guoqiang Wu , Chongxuan Li , Jun Zhu , Bo Zhang

In a real Hilbert space setting, we study the convergence properties of an inexact gradient algorithm featuring both viscous and Hessian driven damping for convex differentiable optimization. In this algorithm, the gradient evaluation can…

Optimization and Control · Mathematics 2025-09-25 Harsh Choudhary , Jalal Fadili , Vyachelav Kungurtsev

We analyze nonlinearly preconditioned gradient methods for solving smooth minimization problems. We introduce a generalized smoothness property, based on the notion of abstract convexity, that is broader than Lipschitz smoothness and…

Optimization and Control · Mathematics 2025-06-18 Konstantinos Oikonomidis , Jan Quan , Emanuel Laude , Panagiotis Patrinos

Adam with decoupled weight decay, also known as AdamW, is widely acclaimed for its superior performance in language modeling tasks, surpassing Adam with $\ell_2$ regularization in terms of generalization and optimization. However, this…

Machine Learning · Computer Science 2024-04-09 Shuo Xie , Zhiyuan Li

We study preconditioning techniques for discontinuous Galerkin discretizations of isotropic linear elasticity problems in primal (displacement) formulation. We propose subspace correction methods based on a splitting of the vector valued…

Numerical Analysis · Mathematics 2011-11-01 Blanca Ayuso de Dios , Ivan Georgiev , Johannes Kraus , Ludmil Zikatanov

We study double descent and benign overfitting in macroeconomic forecasting. We document that double-descent risk curves arise in standard macroeconomic datasets that are driven by a small number of latent factors, and we characterize when…

Econometrics · Economics 2026-05-18 Andrea Carriero , Florian Huber , Davide Pettenuzzo

This paper studies a novel algorithm for nonconvex composite minimization which can be interpreted in terms of dual space nonlinear preconditioning for the classical proximal gradient method. The proposed scheme can be applied to additive…

Optimization and Control · Mathematics 2024-12-24 Emanuel Laude , Panagiotis Patrinos

Gradient regularization (GR) has been shown to improve the generalizability of trained models. While Natural Gradient Descent has been shown to accelerate optimization in the initial phase of training, little attention has been paid to how…

Machine Learning · Computer Science 2026-03-27 Satya Prakash Dash , Hossein Abdi , Wei Pan , Samuel Kaski , Mingfei Sun

Dual averaging and gradient descent with their stochastic variants stand as the two canonical recipe books for first-order optimization: Every modern variant can be viewed as a descendant of one or the other. In the convex regime, these…

Optimization and Control · Mathematics 2025-05-28 Tuo Liu , El Mehdi Saad , Wojciech Kotłowski , Francesco Orabona

Gradient Descent Ascent (GDA) methods are the mainstream algorithms for minimax optimization in generative adversarial networks (GANs). Convergence properties of GDA have drawn significant interest in the recent literature. Specifically,…

Optimization and Control · Mathematics 2022-07-05 Haochuan Li , Farzan Farnia , Subhro Das , Ali Jadbabaie

We consider the noisy matrix sensing problem in the over-parameterization setting, where the estimated rank $r$ is larger than the true rank $r_\star$ of the target matrix $X_\star$. Specifically, our main objective is to recover a matrix $…

Machine Learning · Computer Science 2025-06-03 Zhiyu Liu , Zhi Han , Yandong Tang , Shaojie Tang , Yao Wang

Implicit bias induced by gradient-based algorithms is essential to the generalization of overparameterized models, yet its mechanisms can be subtle. This work leverages the Normalized Steepest Descent} (NSD) framework to investigate how…

Machine Learning · Computer Science 2026-03-25 Shengping Xie , Zekun Wu , Quan Chen , Kaixu Tang

Many supervised machine learning methods are naturally cast as optimization problems. For prediction models which are linear in their parameters, this often leads to convex problems for which many mathematical guarantees exist. Models which…

Machine Learning · Computer Science 2021-10-18 Francis Bach , Lenaïc Chizat

As part of the effort to understand implicit bias of gradient descent in overparametrized models, several results have shown how the training trajectory on the overparametrized model can be understood as mirror descent on a different…

Machine Learning · Computer Science 2022-07-11 Zhiyuan Li , Tianhao Wang , JasonD. Lee , Sanjeev Arora

We develop new sub-optimality bounds for gradient descent (GD) that depend on the conditioning of the objective along the path of optimization rather than on global, worst-case constants. Key to our proofs is directional smoothness, a…

Machine Learning · Computer Science 2025-01-15 Aaron Mishkin , Ahmed Khaled , Yuanhao Wang , Aaron Defazio , Robert M. Gower

Combining empirical risk minimization with capacity control is a classical strategy in machine learning when trying to control the generalization gap and avoid overfitting, as the model class capacity gets larger. Yet, in modern deep…

Machine Learning · Computer Science 2024-03-18 Marc Lafon , Alexandre Thomas

We study the convergence dynamics of Gradient Descent (GD) in a minimal binary classification setting, consisting of a two-neuron ReLU network and two training instances. We prove that even under these strong simplifying assumptions, while…

Machine Learning · Computer Science 2026-03-03 Guy Smorodinsky , Sveta Gimpleson , Itay Safran
‹ Prev 1 8 9 10 Next ›