Online learning for non-monotone DR-submodular maximization: From full information to bandit feedback
In this paper, we revisit the online non-monotone continuous DR-submodular maximization
problem over a down-closed convex set, which finds wide real-world applications in the …
problem over a down-closed convex set, which finds wide real-world applications in the …
An inexact conditional gradient method for constrained bilevel optimization
Bilevel optimization is an important class of optimization problems where one optimization
problem is nested within another. While various methods have emerged to address …
problem is nested within another. While various methods have emerged to address …
Large-scale nonconvex optimization: randomization, gap estimation, and numerical resolution
We address a large-scale and nonconvex optimization problem, involving an aggregative
term. This term can be interpreted as the sum of the contributions of agents to some common …
term. This term can be interpreted as the sum of the contributions of agents to some common …
Zero-order stochastic conditional gradient sliding method for non-smooth convex optimization
A Lobanov, A Anikin, A Gasnikov, A Gornov… - … Optimization Theory and …, 2023 - Springer
The conditional gradient idea proposed by Marguerite Frank and Philip Wolfe in 1956 was
so well received by the community that new algorithms (also called Frank–Wolfe type …
so well received by the community that new algorithms (also called Frank–Wolfe type …
Sequential submodular maximization and applications to ranking an assortment of products
A Asadpour, R Niazadeh, A Saberi… - Operations …, 2023 - pubsonline.informs.org
We study a submodular maximization problem motivated by applications in online retail. A
platform displays a list of products to a user in response to a search query. The user inspects …
platform displays a list of products to a user in response to a search query. The user inspects …
Distributed strategy selection: A submodular set function maximization approach
N Rezazadeh, SS Kia - Automatica, 2023 - Elsevier
Joint utility-maximization problems for multi-agent systems often should be addressed by
distributed strategy-selection formulation. Constrained by discrete feasible strategy sets …
distributed strategy-selection formulation. Constrained by discrete feasible strategy sets …
Sarah frank-wolfe: Methods for constrained optimization with best rates and practical features
The Frank-Wolfe (FW) method is a popular approach for solving optimization problems with
structured constraints that arise in machine learning applications. In recent years, stochastic …
structured constraints that arise in machine learning applications. In recent years, stochastic …
Communication-efficient decentralized online continuous dr-submodular maximization
Maximizing a monotone submodular function is a fundamental task in data mining, machine
learning, economics, and statistics. In this paper, we present two communication-efficient …
learning, economics, and statistics. In this paper, we present two communication-efficient …
Decentralized stochastic projection-free learning with compressed push-sum
R Francis, SP Chepuri - 2023 IEEE 33rd International Workshop …, 2023 - ieeexplore.ieee.org
We consider decentralized stochastic learning methods with data being distributed among
multiple nodes. The nodes communicate gradients with their connected neighbors. To …
multiple nodes. The nodes communicate gradients with their connected neighbors. To …
Stochastic submodular maximization via polynomial estimators
G Özcan, S Ioannidis - Pacific-Asia Conference on Knowledge Discovery …, 2023 - Springer
In this paper, we study stochastic submodular maximization problems with general matroid
constraints, which naturally arise in online learning, team formation, facility location …
constraints, which naturally arise in online learning, team formation, facility location …