FlexiBO: A Decoupled Cost-Aware Multi-Objective Optimization Approach for Deep Neural Networks

DOI10.1613/jair.1.14139arXiv2001.06588OpenAlexW4382792970MaRDI QIDQ6333096

Pooyan Jamshidi, Md Shahriar Iqbal, Jianhai Su, Lars Kotthoff

Publication date: 17 January 2020

Full work available at URL: https://doi.org/10.1613/jair.1.14139

Mathematics Subject Classification ID

Artificial neural networks and deep learning (68T07) Multi-objective and goal programming (90C29)

Cites Work

• Unnamed Item
• Unnamed Item
• Multiple-gradient descent algorithm (MGDA) for multiobjective optimization
• Stochastic method for the solution of unconstrained vector optimization problems
• Efficient global optimization of expensive black-box functions
• Descent algorithm for nonsmooth stochastic multiobjective optimization
• Interactive Thompson sampling for multi-objective multi-armed bandits
• On using the hypervolume indicator to compare Pareto fronts: applications to multi-criteria optimal experimental design
• A Survey of Multi-Objective Sequential Decision-Making
• On Finding the Maxima of a Set of Vectors
• Output Space Entropy Search Framework for Multi-Objective Bayesian Optimization
• Information-Theoretic Regret Bounds for Gaussian Process Optimization in the Bandit Setting
• Advanced Lectures on Machine Learning
• Multiobjective optimization using Gaussian process emulators via stepwise uncertainty reduction

This page was built for publication: FlexiBO: A Decoupled Cost-Aware Multi-Objective Optimization Approach for Deep Neural Networks