English
Related papers

Related papers: Almost Tune-Free Variance Reduction

200 papers

Cubic regularization (CR) is an optimization method with emerging popularity due to its capability to escape saddle points and converge to second-order stationary solutions for nonconvex optimization. However, CR encounters a high sample…

Optimization and Control · Mathematics 2018-10-10 Zhe Wang , Yi Zhou , Yingbin Liang , Guanghui Lan

In this work, we investigate the convergence properties of the backward regularized Wasserstein proximal (BRWP) method for sampling a target distribution. The BRWP approach can be shown as a semi-implicit time discretization for a…

Numerical Analysis · Mathematics 2025-12-18 Fuqun Han , Stanley Osher , Wuchen Li

We study finite-sum nonconvex optimization problems, where the objective function is an average of $n$ nonconvex functions. We propose a new stochastic gradient descent algorithm based on nested variance reduction. Compared with…

Machine Learning · Computer Science 2020-10-20 Dongruo Zhou , Pan Xu , Quanquan Gu

Techniques for reducing the variance of gradient estimates used in stochastic programming algorithms for convex finite-sum problems have received a great deal of attention in recent years. By leveraging dissipativity theory from control, we…

Optimization and Control · Mathematics 2018-06-12 Bin Hu , Stephen Wright , Laurent Lessard

This paper considers both the least squares and quasi-maximum likelihood estimation for the recently proposed scalable ARMA model, a parametric infinite-order vector AR model, and their asymptotic normality is also established. It makes…

Methodology · Statistics 2024-06-28 Yuchang Lin , Wenyu Li , Qianqian Zhu , Guodong Li

Previous approaches to systematic state-space exploration for testing multi-threaded programs have proposed context-bounding and depth-bounding to be effective ranking algorithms for testing multithreaded programs. This paper proposes two…

Programming Languages · Computer Science 2013-02-06 Sandeep Bindal , Sorav Bansal , Akash Lal

During the last decade, incremental sampling-based motion planning algorithms, such as the Rapidly-exploring Random Trees (RRTs) have been shown to work well in practice and to possess theoretical guarantees such as probabilistic…

Robotics · Computer Science 2010-05-05 Sertac Karaman , Emilio Frazzoli

Recent advances in policy gradient methods and deep learning have demonstrated their applicability for complex reinforcement learning problems. However, the variance of the performance gradient estimates obtained from the simulation is…

Machine Learning · Computer Science 2018-03-30 Tianbing Xu , Qiang Liu , Jian Peng

Virtually all state-of-the-art methods for training supervised machine learning models are variants of SGD enhanced with a number of additional tricks, such as minibatching, momentum, and adaptive stepsizes. One of the tricks that works so…

Machine Learning · Computer Science 2021-04-20 Grigory Malinovsky , Alibek Sailanbayev , Peter Richtárik

The Stochastic Extragradient (SEG) method is one of the most popular algorithms for solving finite-sum min-max optimization and variational inequality problems (VIPs) appearing in various machine learning tasks. However, existing…

Optimization and Control · Mathematics 2024-10-11 Konstantinos Emmanouilidis , René Vidal , Nicolas Loizou

The convergence rate is analyzed for the SpaSRA algorithm (Sparse Reconstruction by Separable Approximation) for minimizing a sum $f (\m{x}) + \psi (\m{x})$ where $f$ is smooth and $\psi$ is convex, but possibly nonsmooth. It is shown that…

Optimization and Control · Mathematics 2009-12-10 William Hager , Dzung Phan , Hongchao Zhang

This paper is devoted to proving convergence rates of variational and iterative regularization methods under variational source conditions VSCs for inverse problems whose linearization satisfies a range invariance condition. In order to…

Numerical Analysis · Mathematics 2024-03-28 Barbara Kaltenbacher

We consider a class of optimization problems with Cartesian variational inequality (CVI) constraints, where the objective function is convex and the CVI is associated with a monotone mapping and a convex Cartesian product set. This…

Optimization and Control · Mathematics 2021-02-16 Harshal D. Kaushik , Farzad Yousefian

We consider monotone inclusion problems where the operators may be expectation-valued, a class of problems that subsumes convex stochastic optimization problems as well as subclasses of stochastic variational inequality and equilibrium…

Optimization and Control · Mathematics 2021-10-19 Shisheng Cui , Uday V. Shanbhag

Sharpness-aware minimization (SAM) has emerged as a highly effective technique to improve model generalization, but its underlying principles are not fully understood. We investigate m-sharpness, where SAM performance improves monotonically…

Machine Learning · Computer Science 2026-04-03 Haocheng Luo , Mehrtash Harandi , Dinh Phung , Trung Le

Thresholding based iterative algorithms have the trade-off between effectiveness and optimality. Some are effective but involving sub-matrix inversions in every step of iterations. For systems of large sizes, such algorithms can be…

Information Theory · Computer Science 2017-11-08 Zhanjie Song , Shidong Li , Ningning Han

We show that, for finite-sum minimization problems, incorporating partial second-order information of the objective function can dramatically improve the robustness to mini-batch size of variance-reduced stochastic gradient methods, making…

Optimization and Control · Mathematics 2024-04-24 Sachin Garg , Albert S. Berahas , Michał Dereziński

This paper develops new variance-reduction techniques for the forward-reflected-backward splitting (FRBS) method to solve a class of possibly nonmonotone stochastic composite inclusions. Unlike unbiased estimators such as mini-batching,…

Machine Learning · Computer Science 2026-03-17 Quoc Tran-Dinh , Nghia Nguyen-Trung

Algorithms to solve variational regularization of ill-posed inverse problems usually involve operators that depend on a collection of continuous parameters. When these operators enjoy some (local) regularity, these parameters can be…

Statistics Theory · Mathematics 2014-08-12 Charles-Alban Deledalle , Samuel Vaiter , Jalal M. Fadili , Gabriel Peyré

By driving models to converge to flat minima, sharpness-aware learning algorithms (such as SAM) have shown the power to achieve state-of-the-art performances. However, these algorithms will generally incur one extra forward-backward…

Machine Learning · Computer Science 2023-04-11 Yang Zhao , Hao Zhang , Xiuyuan Hu