B\'ezier Flow: a Surface-wise Gradient Descent Method for Multi-objective Optimization
Optimization and Control
2022-05-24 v1 Machine Learning
Abstract
In this paper, we propose a strategy to construct a multi-objective optimization algorithm from a single-objective optimization algorithm by using the B\'ezier simplex model. Also, we extend the stability of optimization algorithms in the sense of Probability Approximately Correct (PAC) learning and define the PAC stability. We prove that it leads to an upper bound on the generalization with high probability. Furthermore, we show that multi-objective optimization algorithms derived from a gradient descent-based single-objective optimization algorithm are PAC stable. We conducted numerical experiments and demonstrated that our method achieved lower generalization errors than the existing multi-objective optimization algorithm.
Keywords
Cite
@article{arxiv.2205.11099,
title = {B\'ezier Flow: a Surface-wise Gradient Descent Method for Multi-objective Optimization},
author = {Akiyoshi Sannai and Yasunari Hikima and Ken Kobayashi and Akinori Tanaka and Naoki Hamada},
journal= {arXiv preprint arXiv:2205.11099},
year = {2022}
}