Please use this identifier to cite or link to this item: https://scholarbank.nus.edu.sg/handle/10635/211398
DC FieldValue
dc.titleProfiling pareto front with multi-objective stein variational gradient descent
dc.contributor.authorLiu, Xingchao
dc.contributor.authorTONG XIN
dc.contributor.authorLiu, Qiang
dc.date.accessioned2021-12-22T01:41:43Z
dc.date.available2021-12-22T01:41:43Z
dc.date.issued2021-12-06
dc.identifier.citationLiu, Xingchao, TONG XIN, Liu, Qiang (2021-12-06). Profiling pareto front with multi-objective stein variational gradient descent. Neural Information Processing Systems. ScholarBank@NUS Repository.
dc.identifier.urihttps://scholarbank.nus.edu.sg/handle/10635/211398
dc.description.abstractFinding diverse and representative Pareto solutions from the Pareto front is a key challenge in multi-objective optimization (MOO). In this work, we propose a novel gradient-based algorithm for profiling Pareto front by using Stein variational gradient descent (SVGD). We also provide a counterpart of our method based on Langevin dynamics. Our methods iteratively update a set of points in a parallel fashion to push them towards the Pareto front using multiple gradient descent, while encouraging the diversity between the particles by using the repulsive force mechanism in SVGD, or diffusion noise in Langevin dynamics. Compared with existing gradient-based methods that require predefined preference functions, our method can work efficiently in high dimensional problems, and can obtain more diverse solutions evenly distributed in the Pareto front. Moreover, our methods are theoretically guaranteed to converge to the Pareto front. We demonstrate the effectiveness of our method, especially the SVGD algorithm, through extensive experiments, showing its superiority over existing gradient-based algorithms.
dc.publisherNeurIPS 2021 Thirty-fifth Conference on Neural Information Processing Systems
dc.sourceElements
dc.typeConference Paper
dc.date.updated2021-12-21T09:12:50Z
dc.contributor.departmentMATHEMATICS
dc.description.sourcetitleNeural Information Processing Systems
dc.published.statePublished
Appears in Collections:Staff Publications
Elements

Show simple item record
Files in This Item:
File Description SizeFormatAccess SettingsVersion 
NeurIPS-2021-profiling-pareto-front-with-multi-objective-stein-variational-gradient-descent-Paper.pdf6.9 MBAdobe PDF

OPEN

Pre-printView/Download

Google ScholarTM

Check


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.