Follow the bisector: a simple method for multi-objective optimization
Optimization and Control
2020-07-15 v1 Machine Learning
Abstract
This study presents a novel Equiangular Direction Method (EDM) to solve a multi-objective optimization problem. We consider optimization problems, where multiple differentiable losses have to be minimized. The presented method computes descent direction in every iteration to guarantee equal relative decrease of objective functions. This descent direction is based on the normalized gradients of the individual losses. Therefore, it is appropriate to solve multi-objective optimization problems with multi-scale losses. We test the proposed method on the imbalanced classification problem and multi-task learning problem, where standard datasets are used. EDM is compared with other methods to solve these problems.
Cite
@article{arxiv.2007.06937,
title = {Follow the bisector: a simple method for multi-objective optimization},
author = {Alexandr Katrutsa and Daniil Merkulov and Nurislam Tursynbek and Ivan Oseledets},
journal= {arXiv preprint arXiv:2007.06937},
year = {2020}
}