Regularized Unconstrained Weakly Submodular Maximization

Submodular optimization finds applications in machine learning and data mining. In this paper, we study the problem of maximizing functions of the form \(h = f-c\), where \(f\) is a monotone, non-negative, weakly submodular set function and \(c\) is a modular function. We design a deterministic appr...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:arXiv.org
Hlavní autori: Zhu, Yanhui, Basu, Samik, Pavan, A
Médium: Paper
Jazyk:English
Vydavateľské údaje: Ithaca Cornell University Library, arXiv.org 19.08.2024
Predmet:
Algorithms
Approximation
Data mining
Machine learning
Maximization
Optimization
ISSN:2331-8422
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Popis
Shrnutí:Submodular optimization finds applications in machine learning and data mining. In this paper, we study the problem of maximizing functions of the form \(h = f-c\), where \(f\) is a monotone, non-negative, weakly submodular set function and \(c\) is a modular function. We design a deterministic approximation algorithm that runs with \({{O}}(\frac{n}{\epsilon}\log \frac{n}{\gamma \epsilon})\) oracle calls to function \(h\), and outputs a set \({S}\) such that \(h({S}) \geq \gamma(1-\epsilon)f(OPT)-c(OPT)-\frac{c(OPT)}{\gamma(1-\epsilon)}\log\frac{f(OPT)}{c(OPT)}\), where \(\gamma\) is the submodularity ratio of \(f\). Existing algorithms for this problem either admit a worse approximation ratio or have quadratic runtime. We also present an approximation ratio of our algorithm for this problem with an approximate oracle of \(f\). We validate our theoretical results through extensive empirical evaluations on real-world applications, including vertex cover and influence diffusion problems for submodular utility function \(f\), and Bayesian A-Optimal design for weakly submodular \(f\). Our experimental results demonstrate that our algorithms efficiently achieve high-quality solutions.
Bibliografia:SourceType-Working Papers-1
ObjectType-Working Paper/Pre-Print-1
content type line 50
ISSN:2331-8422
DOI:10.48550/arxiv.2408.04620