中文
相关论文

相关论文: Stochastic Variance-reduced Gradient Descent for L…

200 篇论文

We consider the problem of estimating the factors of a rank-$1$ matrix with i.i.d. Gaussian, rank-$1$ measurements that are nonlinearly transformed and corrupted by noise. Considering two prototypical choices for the nonlinearity, we study…

最优化与控制 · 数学 2024-10-02 Kabir Aladin Chandrasekher , Mengqi Lou , Ashwin Pananjady

The graduated optimization approach is a method for finding global optimal solutions for nonconvex functions by using a function smoothing operation with stochastic noise. This paper makes three contributions regarding graduated…

机器学习 · 计算机科学 2026-01-27 Naoki Sato , Hideaki Iiduka

This paper is devoted to a new modification of a recently proposed adaptive stochastic mirror descent algorithm for constrained convex optimization problems in the case of several convex functional constraints. Algorithms, standard and its…

最优化与控制 · 数学 2020-01-22 Mohammad S. Alkousa

We study stochastic optimization of nonconvex loss functions, which are typical objectives for training neural networks. We propose stochastic approximation algorithms which optimize a series of regularized, nonlinearized losses on large…

机器学习 · 计算机科学 2019-03-12 Weiran Wang , Nathan Srebro

Motivated by the desire to understand stochastic algorithms for nonconvex optimization that are robust to their hyperparameter choices, we analyze a mini-batched prox-linear iterative algorithm for the problem of recovering an unknown…

最优化与控制 · 数学 2024-02-05 Mengqi Lou , Kabir Aladin Verchand , Ashwin Pananjady

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

Matrix recovery from sparse observations is an extensively studied topic emerging in various applications, such as recommendation system and signal processing, which includes the matrix completion and compressed sensing models as special…

统计方法学 · 统计学 2026-04-13 Ziyuan Chen , Ying Yang , Fang Yao

We propose a prox-regular-type low-rank constrained nonconvex nonsmooth optimization model for Robust Low-Rank Matrix Recovery (RLRMR), i.e., estimate problem of low-rank matrix from an observed signal corrupted by outliers. For RLRMR, the…

最优化与控制 · 数学 2026-02-03 Keita Kume , Isao Yamada

We develop a distributed stochastic gradient descent algorithm for solving non-convex optimization problems under the assumption that the local objective functions are twice continuously differentiable with Lipschitz continuous gradients…

最优化与控制 · 数学 2019-08-20 Jemin George , Tao Yang , He Bai , Prudhvi Gurram

Robust tensor recovery plays an instrumental role in robustifying tensor decompositions for multilinear data analysis against outliers, gross corruptions and missing values and has a diverse array of applications. In this paper, we study…

机器学习 · 统计学 2014-08-26 Donald Goldfarb , Zhiwei Qin

We consider a structured estimation problem where an observed matrix is assumed to be generated as an $s$-sparse linear combination of $N$ given $n\times n$ positive-semidefinite matrices. Recovering the unknown $N$-dimensional and…

信息论 · 计算机科学 2020-03-27 Fabian Jaensch , Peter Jung

We study a class of stochastic nonconvex optimization in the form of $\min_{x\in\mathcal{X}} F(x):=\mathbb{E}_\xi [f(\phi(x,\xi))]$, i.e., $F$ is a composition of a convex function $f$ and a random function $\phi$. Leveraging an (implicit)…

最优化与控制 · 数学 2024-07-16 Xin Chen , Niao He , Yifan Hu , Zikun Ye

Projected gradient descent and its Riemannian variant belong to a typical class of methods for low-rank matrix estimation. This paper proposes a new Nesterov's Accelerated Riemannian Gradient algorithm by efficient orthographic retraction…

最优化与控制 · 数学 2023-06-05 Hongyi Li , Zhen Peng , Chengwei Pan , Di Zhao

We design a non-convex second-order optimization algorithm that is guaranteed to return an approximate local minimum in time which scales linearly in the underlying dimension and the number of training examples. The time complexity of our…

最优化与控制 · 数学 2017-04-26 Naman Agarwal , Zeyuan Allen-Zhu , Brian Bullins , Elad Hazan , Tengyu Ma

We investigate the stochastic optimization problem of minimizing population risk, where the loss defining the risk is assumed to be weakly convex. Compositions of Lipschitz convex functions with smooth maps are the primary examples of such…

最优化与控制 · 数学 2018-12-19 Damek Davis , Dmitriy Drusvyatskiy

This paper introduces a new method for minimizing matrix-smooth non-convex objectives through the use of novel Compressed Gradient Descent (CGD) algorithms enhanced with a matrix-valued stepsize. The proposed algorithms are theoretically…

最优化与控制 · 数学 2024-04-23 Hanmin Li , Avetik Karagulyan , Peter Richtárik

The stochastic subgradient method is a widely-used algorithm for solving large-scale optimization problems arising in machine learning. Often these problems are neither smooth nor convex. Recently, Davis et al. [1-2] characterized the…

最优化与控制 · 数学 2021-02-25 Shixiang Chen , Alfredo Garcia , Shahin Shahrampour

In this paper we propose several adaptive gradient methods for stochastic optimization. Unlike AdaGrad-type of methods, our algorithms are based on Armijo-type line search and they simultaneously adapt to the unknown Lipschitz constant of…

In this paper we propose a variant of the random coordinate descent method for solving linearly constrained convex optimization problems with composite objective functions. If the smooth part of the objective function has Lipschitz…

最优化与控制 · 数学 2013-02-14 Ion Necoara , Andrei Patrascu

Subspace learning and matrix factorization problems have great many applications in science and engineering, and efficient algorithms are critical as dataset sizes continue to grow. Many relevant problem formulations are non-convex, and in…

数值分析 · 计算机科学 2022-02-22 Dejiao Zhang , Laura Balzano