中文
相关论文

相关论文: Particle Dual Averaging: Optimization of Mean Fiel…

200 篇论文

We establish the first global convergence result of neural networks for two stage least squares (2SLS) approach in nonparametric instrumental variable regression (NPIV). This is achieved by adopting a lifted perspective through mean-field…

机器学习 · 统计学 2025-11-19 Zonghao Chen , Atsushi Nitanda , Arthur Gretton , Taiji Suzuki

We propose an algorithm for optimizing the parameters of single hidden layer neural networks. Specifically, we derive a blockwise difference-of-convex (DC) functions representation of the objective function. Based on the latter, we propose…

机器学习 · 计算机科学 2024-01-17 Daniel Tschernutter , Mathias Kraus , Stefan Feuerriegel

We study reinforcement learning by combining recent advances in regularized linear programming formulations with the classical theory of stochastic approximation. Motivated by the challenge of designing algorithms that leverage off-policy…

最优化与控制 · 数学 2026-04-15 Axel Friedrich Wolter , Tobias Sutter

In this paper, we propose a novel Dual Inexact Splitting Algorithm (DISA) for distributed convex composite optimization problems, where the local loss function consists of a smooth term and a possibly nonsmooth term composed with a linear…

最优化与控制 · 数学 2023-04-25 Luyao Guo , Xinli Shi , Shaofu Yang , Jinde Cao

Many engineering processes can be accurately modelled using partial differential equations (PDEs), but high dimensionality and non-convexity of the resulting systems pose limitations on their efficient optimisation. In this work, a model…

最优化与控制 · 数学 2024-10-17 Min Tao , Panagiotis Petsagkourakis , Jie Li , Constantinos Theodoropoulos

This paper aims to develop distributed algorithms for nonconvex optimization problems with complicated constraints associated with a network. The network can be a physical one, such as an electric power network, where the constraints are…

最优化与控制 · 数学 2022-11-21 Kaizhao Sun , X. Andy Sun

We study learning to learn for regression problems through the lens of hyperparameter tuning. We propose the Langevin Gradient Descent Algorithm (LGD), which approximates the mean of the posterior distribution defined by the loss function…

机器学习 · 计算机科学 2026-04-16 Saumya Goyal , Rohith Rongali , Ritabrata Ray , Barnabás Póczos

Sampling from a high-dimensional distribution is a fundamental task in statistics, engineering, and the sciences. A canonical approach is the Langevin Algorithm, i.e., the Markov chain for the discretized Langevin Diffusion. This is the…

统计理论 · 数学 2022-11-01 Jason M. Altschuler , Kunal Talwar

We present new analysis and algorithm of the dual-averaging-type (DA-type) methods for solving the composite convex optimization problem ${\min}_{x\in\mathbb{R}^n} \, f(\mathsf{A} x) + h(x)$, where $f$ is a convex and globally Lipschitz…

最优化与控制 · 数学 2025-05-06 Renbo Zhao

The success of minimax learning problems of generative adversarial networks (GANs) has been observed to depend on the minimax optimization algorithm used for their training. This dependence is commonly attributed to the convergence speed…

机器学习 · 计算机科学 2020-10-26 Farzan Farnia , Asuman Ozdaglar

Gradient descent ascent (GDA), the simplest single-loop algorithm for nonconvex minimax optimization, is widely used in practical applications such as generative adversarial networks (GANs) and adversarial training. Albeit its desirable…

机器学习 · 计算机科学 2021-12-13 Junchi Yang , Antonio Orvieto , Aurelien Lucchi , Niao He

In this paper we propose and analyze two dual methods based on inexact gradient information and averaging that generate approximate primal solutions for smooth convex optimization problems. The complicating constraints are moved into the…

最优化与控制 · 数学 2013-02-14 Ion Necoara , Valentin Nedelcu

When equipped with efficient optimization algorithms, the over-parameterized neural networks have demonstrated high level of performance even though the loss function is non-convex and non-smooth. While many works have been focusing on…

机器学习 · 计算机科学 2021-03-11 Zhiqi Bu , Shiyun Xu , Kan Chen

The mean-field Langevin dynamics (MFLD) minimizes an entropy-regularized nonlinear convex functional on the Wasserstein space over $\mathbb{R}^d$, and has gained attention recently as a model for the gradient descent dynamics of interacting…

机器学习 · 计算机科学 2026-05-19 Anming Gu , Juno Kim

In the mean field regime, neural networks are appropriately scaled so that as the width tends to infinity, the learning dynamics tends to a nonlinear and nontrivial dynamical limit, known as the mean field limit. This lends a way to study…

机器学习 · 计算机科学 2021-05-12 Huy Tuan Pham , Phan-Minh Nguyen

In the field of global optimization, many existing algorithms face challenges posed by non-convex target functions and high computational complexity or unavailability of gradient information. These limitations, exacerbated by sensitivity to…

最优化与控制 · 数学 2023-10-16 Xinyu Zhang , Sujit Ghosh

We tackle the general differentiable meta learning problem that is ubiquitous in modern deep learning, including hyperparameter optimization, loss function learning, few-shot learning, invariance learning and more. These problems are often…

机器学习 · 计算机科学 2024-10-15 Minyoung Kim , Timothy M. Hospedales

Nonconvex-nonconcave minimax optimization has received intense attention over the last decade due to its broad applications in machine learning. Most existing algorithms rely on one-sided information, such as the convexity (resp. concavity)…

最优化与控制 · 数学 2023-10-31 Taoli Zheng , Linglingzhi Zhu , Anthony Man-Cho So , Jose Blanchet , Jiajin Li

In this paper, we develop unrolled neural networks to solve constrained optimization problems, offering accelerated, learnable counterparts to dual ascent (DA) algorithms. Our framework, termed constrained dual unrolling (CDU), comprises…

机器学习 · 计算机科学 2026-01-27 Samar Hadou , Alejandro Ribeiro

This work studies nonconvex distributed constrained optimization over stochastic communication networks. We revisit the distributed dual averaging algorithm, which is known to converge for convex problems. We start from the centralized…

最优化与控制 · 数学 2022-11-15 Changxin Liu , Xuyang Wu , Xinlei Yi , Yang Shi , Karl H. Johansson