paper-with-me

Papers

Stochastic Variance-Reduced Iterative Hard Thresholding in Graph Sparsity Optimization

2024-07-24 · Derek Fox, Samuel Hernandez, Qianqian Tong

Stochastic optimization algorithms are widely used for large-scale data analysis due to their low per-iteration costs, but they often suffer from slow asymptotic convergence caused by inherent variance. Variance-reduced techniques have been therefore used to address this issue in structured sparse models utilizing sparsity-inducing norms or $\ell_0$-norms. However, these techniques are not directly applicable to complex (non-convex) graph sparsity models, which are essential in applications like disease outbreak monitoring and social network analysis. In this paper, we introduce two stochastic variance-reduced gradient-based methods to solve graph sparsity optimization: GraphSVRG-IHT and GraphSCSG-IHT. We provide a general framework for theoretical analysis, demonstrating that our methods enjoy a linear convergence speed. Extensive experiments validate

📄 PDF Abstract BibTeX arXiv:2407.16968

Code (1)

derek-fox/graph-scsg-iht 공식 구현

Tasks

Stochastic Optimization

Similar Papers 제목 키워드 기반

A Coordinate-wise Optimization Algorithm for Sparse Inverse Covariance Selection

2017-11-19 · Ganzhao Yuan, Haoxian Tan, Wei-Shi Zheng

Sparse inverse covariance selection is a fundamental problem for analyzing dependencies in high dimensional data. However, such a problem is difficult to solve since it is NP-hard. Existing solutions are primarily based …

New Insight of Variance reduce in Zero-Order Hard-Thresholding: Mitigating Gradient Error and Expansivity Contradictions

2026-05-18 · Xinzhe Yuan, William de Vazelhes, Bin Gu, Huan Xiong arxiv

Hard-thresholding is an important type of algorithm in machine learning that is used to solve $\ell_0$ constrained optimization problems. However, the true gradient of the objective function can be difficult to access in…

Adaptive Iterative Hard Thresholding for Online High-dimensional Quantile Regression

2026-06-26 · Zitian Zhou, Nan Lin arxiv

Online high-dimensional regression requires algorithms that can update sequentially while preserving structural sparsity. We propose \textit{Adaptive Iterative Hard Thresholding (AIHT)}, an online sparse-regression frame…

Efficient Stochastic Gradient Hard Thresholding

2018-12-01 · NeurIPS 2018 12 · Pan Zhou, Xiao-Tong Yuan, Jiashi Feng

Stochastic gradient hard thresholding methods have recently been shown to work favorably in solving large-scale empirical risk minimization problems under sparsity or rank constraint. Despite the improved iteration compl…

Computational Efficiency

Between hard and soft thresholding: optimal iterative thresholding algorithms

2018-04-24 · Haoyang Liu, Rina Foygel Barber

Iterative thresholding algorithms seek to optimize a differentiable objective function over a sparsity or rank constraint by alternating between gradient steps that reduce the objective, and thresholding steps that enfor…