中文
相关论文

相关论文: Small steps no more: Global convergence of stochas…

200 篇论文

We show that the \emph{stochastic gradient} bandit algorithm converges to a \emph{globally optimal} policy at an $O(1/t)$ rate, even with a \emph{constant} step size. Remarkably, global convergence of the stochastic gradient bandit…

机器学习 · 计算机科学 2024-02-28 Jincheng Mei , Zixin Zhong , Bo Dai , Alekh Agarwal , Csaba Szepesvari , Dale Schuurmans

Bandit based optimisation has a remarkable advantage over gradient based approaches due to their global perspective, which eliminates the danger of getting stuck at local optima. However, for continuous optimisation problems or problems…

人工智能 · 计算机科学 2017-05-30 Ole-Christoffer Granmo

Gradient descent and stochastic gradient descent are central to modern machine learning, yet their behavior under large step sizes remains theoretically unclear. Recent work suggests that acceleration often arises near the edge of…

机器学习 · 计算机科学 2026-03-02 Sacchit Kale , Piyushi Manupriya , Pierre Marion , Francis Bach , Anant Raj

Stochastic gradient descent is the method of choice for large scale optimization of machine learning objective functions. Yet, its performance is greatly variable and heavily depends on the choice of the stepsizes. This has motivated a…

机器学习 · 统计学 2019-02-28 Xiaoyu Li , Francesco Orabona

Online minimization of an unknown convex function over the interval $[0,1]$ is considered under first-order stochastic bandit feedback, which returns a random realization of the gradient of the function at each query point. Without knowing…

机器学习 · 统计学 2020-02-21 Sattar Vakili , Sudeep Salgia , Qing Zhao

When training neural networks, it has been widely observed that a large step size is essential in stochastic gradient descent (SGD) for obtaining superior models. However, the effect of large step sizes on the success of SGD is not well…

机器学习 · 计算机科学 2023-02-17 Amirkeivan Mohtashami , Martin Jaggi , Sebastian Stich

We investigate the stochastic gradient descent (SGD) method where the step size lies within a banded region instead of being given by a fixed formula. The optimal convergence rate under mild conditions and large initial step size is proved.…

最优化与控制 · 数学 2023-04-10 Xiaoyu Wang , Ya-xiang Yuan

Large-scale optimization problems require algorithms both effective and efficient. One such popular and proven algorithm is Stochastic Gradient Descent which uses first-order gradient information to solve these problems. This paper studies…

最优化与控制 · 数学 2021-11-11 Theodoros Mamalis , Dusan Stipanovic , Petros Voulgaris

The analysis in Part I revealed interesting properties for subgradient learning algorithms in the context of stochastic optimization when gradient noise is present. These algorithms are used when the risk functions are non-smooth and…

最优化与控制 · 数学 2017-04-21 Bicheng Ying , Ali H. Sayed

In empirical risk optimization, it has been observed that stochastic gradient implementations that rely on random reshuffling of the data achieve better performance than implementations that rely on sampling the data uniformly. Recent works…

机器学习 · 计算机科学 2019-01-30 Bicheng Ying , Kun Yuan , Stefan Vlaski , Ali H. Sayed

We consider (stochastic) softmax policy gradient (PG) methods for bandits and tabular Markov decision processes (MDPs). While the PG objective is non-concave, recent research has used the objective's smoothness and gradient domination…

机器学习 · 计算机科学 2024-10-01 Michael Lu , Matin Aghaei , Anant Raj , Sharan Vaswani

We study the problem of minimizing a strongly convex, smooth function when we have noisy estimates of its gradient. We propose a novel multistage accelerated algorithm that is universally optimal in the sense that it achieves the optimal…

最优化与控制 · 数学 2019-10-29 Necdet Serhat Aybat , Alireza Fallah , Mert Gurbuzbalaban , Asuman Ozdaglar

Recently, it has been shown that the Stochastic Gradient Bandit (SGB) algorithm converges to a globally optimal policy with a constant learning rate. However, these guarantees rely on unrealistic assumptions about the learning process,…

机器学习 · 计算机科学 2026-05-11 Leonardo Cesani , Matteo Papini , Marcello Restelli

We introduce a new model of stochastic bandits with adversarial corruptions which aims to capture settings where most of the input follows a stochastic pattern but some fraction of it can be adversarially changed to trick the algorithm,…

机器学习 · 计算机科学 2018-03-28 Thodoris Lykouris , Vahab Mirrokni , Renato Paes Leme

Stochastic gradient methods enable learning probabilistic models from large amounts of data. While large step-sizes (learning rates) have shown to be best for least-squares (e.g., Gaussian noise) once combined with parameter averaging,…

机器学习 · 统计学 2018-11-22 Dmitry Babichev , Francis Bach

Recent work has established an empirically successful framework for adapting learning rates for stochastic gradient descent (SGD). This effectively removes all needs for tuning, while automatically reducing learning rates over time on…

机器学习 · 计算机科学 2013-03-28 Tom Schaul , Yann LeCun

This paper proposes a stochastic gradient descent method with an adaptive Gaussian noise term for the global minimization of nearly convex functions, which are nonconvex and possess multiple strict local minimizers. The noise term,…

最优化与控制 · 数学 2025-08-05 Chenglong Bao , Liang Chen , Weizhi Shao

Many stochastic optimization algorithms work by estimating the gradient of the cost function on the fly by sampling datapoints uniformly at random from a training set. However, the estimator might have a large variance, which inadvertently…

机器学习 · 计算机科学 2017-08-10 Farnood Salehi , L. Elisa Celis , Patrick Thiran

Under mild assumptions stochastic gradient methods asymptotically achieve an optimal rate of convergence if the arithmetic mean of all iterates is returned as an approximate optimal solution. However, in the absence of stochastic noise, the…

最优化与控制 · 数学 2022-10-06 Melinda Hagedorn , Florian Jarre

In the setting of nonparametric regression, we propose and study a combination of stochastic gradient methods with Nystr\"om subsampling, allowing multiple passes over the data and mini-batches. Generalization error bounds for the studied…

机器学习 · 统计学 2017-10-24 Junhong Lin , Lorenzo Rosasco
‹ 上一页 1 2 3 10 下一页 ›