中文
相关论文

相关论文: Adaptive Stochastic Natural Gradient Method for Sa…

200 篇论文

Adaptive moment methods have been remarkably successful in deep learning optimization, particularly in the presence of noisy and/or sparse gradients. We further the advantages of adaptive moment techniques by proposing a family of double…

机器学习 · 统计学 2018-11-07 Kin Gutierrez , Jin Li , Cristian Challu , Artur Dubrawski

We consider regression problems with binary weights. Such optimization problems are ubiquitous in quantized learning models and digital communication systems. A natural approach is to optimize the corresponding Lagrangian using variants of…

机器学习 · 计算机科学 2020-12-01 Nisan Chiprut , Amir Globerson , Ami Wiesel

Consider composite nonconvex optimization problems where the objective function consists of a smooth nonconvex term (with Lipschitz-continuous gradient) and a convex (possibly nonsmooth) term. Existing parameter-free methods for such…

最优化与控制 · 数学 2025-10-08 Zilong Ye , Shiqian Ma , Junfeng Yang , Danqing Zhou

For solving pseudo-convex global optimization problems, we present a novel fully adaptive steepest descent method (or ASDM) without any hard-to-estimate parameters. For the step-size regulation in an $\varepsilon$-normalized direction, we…

最优化与控制 · 数学 2021-08-12 Z. R. Gabidullina

Parametric manifold optimization problems frequently arise in various machine learning tasks, where state functions are defined on infinite-dimensional manifolds. We propose a unified accelerated natural gradient descent (ANGD) framework to…

最优化与控制 · 数学 2025-04-09 Chenyi Li , Shuchen Zhu , Zhonglin Xie , Zaiwen Wen

We propose a stochastic optimization method for minimizing loss functions, expressed as an expected value, that adaptively controls the batch size used in the computation of gradient approximations and the step size used to move along such…

机器学习 · 计算机科学 2020-03-04 Achraf Bahamou , Donald Goldfarb

The training of deep neural networks is inherently a nonconvex optimization problem, yet standard approaches such as stochastic gradient descent (SGD) require simultaneous updates to all parameters, often leading to unstable convergence and…

机器学习 · 计算机科学 2025-08-07 Chengcheng Yan , Jiawei Xu , Zheng Peng , Qingsong Wang

Alternating direction method of multipliers (ADMM) is a popular optimization tool for the composite and constrained problems in machine learning. However, in many machine learning problems such as black-box attacks and bandit feedback, ADMM…

最优化与控制 · 数学 2019-07-31 Feihu Huang , Shangqian Gao , Songcan Chen , Heng Huang

We propose a novel gradient-based online optimization framework for solving stochastic programming problems that frequently arise in the context of cyber-physical and robotic systems. Our problem formulation accommodates constraints that…

机器学习 · 计算机科学 2026-01-06 Hao Ma , Melanie Zeilinger , Michael Muehlebach

Asynchronous stochastic gradient descent (ASGD) is a popular parallel optimization algorithm in machine learning. Most theoretical analysis on ASGD take a discrete view and prove upper bounds for their convergence rates. However, the…

机器学习 · 统计学 2018-05-09 Li He , Qi Meng , Wei Chen , Zhi-Ming Ma , Tie-Yan Liu

In this paper, we utilize stochastic optimization to reduce the space complexity of convex composite optimization with a nuclear norm regularizer, where the variable is a matrix of size $m \times n$. By constructing a low-rank estimate of…

机器学习 · 计算机科学 2015-12-08 Lijun Zhang , Tianbao Yang , Rong Jin , Zhi-Hua Zhou

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…

最优化与控制 · 数学 2020-03-12 Long Chen , Wenyi Chen , Kai-Uwe Bletzinger

Stochastic Optimization is a cornerstone of operations research, providing a framework to solve optimization problems under uncertainty. Despite the development of numerous algorithms to tackle these problems, several persistent challenges…

最优化与控制 · 数学 2025-03-28 Di Zhang , Suvrajeet Sen

Optimization algorithms are pivotal in advancing various scientific and industrial fields but often encounter obstacles such as trapping in local minima, saddle points, and plateaus (flat regions), which makes the convergence to reasonable…

最优化与控制 · 数学 2026-01-15 Amir M. Vahedi , Horea T. Ilies

Bayesian optimization has recently emerged as a popular and efficient tool for global optimization and hyperparameter tuning. Currently, the established Bayesian optimization practice requires a user-defined bounding box which is assumed to…

机器学习 · 统计学 2015-08-18 Bobak Shahriari , Alexandre Bouchard-Côté , Nando de Freitas

Topology optimization under uncertainty (TOuU) often defines objectives and constraints by statistical moments of geometric and physical quantities of interest. Most traditional TOuU methods use gradient-based optimization algorithms and…

最优化与控制 · 数学 2019-11-05 Subhayan De , Jerrad Hampton , Kurt Maute , Alireza Doostan

In this paper, we introduce a new stochastic approximation (SA) type algorithm, namely the randomized stochastic gradient (RSG) method, for solving an important class of nonlinear (possibly nonconvex) stochastic programming (SP) problems.…

最优化与控制 · 数学 2015-10-27 Saeed Ghadimi , Guanghui Lan

Stochastic gradient descent (SGD) optimization methods such as the plain vanilla SGD method and the popular Adam optimizer are nowadays the method of choice in the training of artificial neural networks (ANNs). Despite the remarkable…

最优化与控制 · 数学 2024-02-09 Arnulf Jentzen , Adrian Riekert

We propose a novel stochastic smoothing accelerated gradient (SSAG) method for general constrained nonsmooth convex composite optimization, and analyze the convergence rates. The SSAG method allows various smoothing techniques, and can deal…

最优化与控制 · 数学 2026-02-03 Ruyu Wang , Chao Zhang

Binary optimisation tasks are ubiquitous in areas ranging from logistics to cryptography. The exponential complexity of such problems means that the performance of traditional computational methods decreases rapidly with increasing problem…