Multi-objective Optimization

By Carlos Artemio Coello Coello. 2018

1,372 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Optimization & Training

Citations in the corpus

Concrete Problems in AI Safety (2016, background): “• Multiple Rewards: A combination of multiple rewards [40] may be more difficult to hack and more robust.”
MnasNet: Platform-Aware Neural Architecture Search for Mobile (2018, methodology): “While there are many methods in the literature [2], we use a customized weighted product method1 to approximate Pareto optimal solutions, with optimization goal defined as:”
Approximating Interactive Human Evaluation with Self-Play for Open-Domain Dialog Systems (2019, background): “On a realistic conversation trajectory, M H is a hybrid of conﬂicting objectives and thus is less susceptible to exploitation [40].”
A Comprehensive Survey on Fog Computing: State-of-the-Art and Research Challenges (2017, background): “To study these problems, one research direction is to consider multi-objective optimization strategies [150], in order to derive optimal solutions in the presence of trade-offs between various objectives.”
UAV path planning using artificial potential field method updated by optimal control theory (2016, positive): “The UAV optimisation cost function is a multi-objective optimisation function (Aitsaadi et al., 2011; Deb, 2005).”
Hierarchical Reinforcement Learning for Open-Domain Dialog (2019, background): “By optimizing a combination of these rewards with sometimes conﬂicting objectives (as we explore in Section 7.1), we can show that the reward function is difﬁcult to trivially exploit, as suggested by Deb (2014).”
A Vector Angle-Based Evolutionary Algorithm for Unconstrained Many-Objective Optimization (2017, methodology): “For ∀ x ∈ PS, its objective vector F(x) constitutes the Pareto front (PF) [16].”
Multi-Objective Evolutionary Federated Learning (2018, methodology): “We reformulate federated learning as a two objective optimization problem [35].”
Review of numerical optimization techniques for meta-device design [Invited] (2019, methodology): “Furthermore, both local and global optimization techniques have been extended to support true multi-objective optimization [24], which is a powerful emerging technique in meta-device design.”
Test Problems for Large-Scale Multiobjective and Many-Objective Optimization (2017, neutral): “MOEAs [60]–[63].”
Training Spiking Neural Networks Using Lessons From Deep Learning (2021, background): “How the brain can be optimized using these objectives remains a mystery though we might gain insight from multiobjective optimization [125].”
Grasshopper optimization algorithm for multi-objective optimization problems (2017, background): “This is a key feature in a posteriori multi-objective algorithms [24] where decision making [25] occurs after the optimization.”