Follow the bisector: a simple method for multi-objective optimization

07/14/2020
by   Alexandr Katrutsa, et al.
0

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.

READ FULL TEXT
research
10/07/2021

Explicitly Multi-Modal Benchmarks for Multi-Objective Optimization

We model multi-modality in multi-objective optimization problems and app...
research
05/25/2021

An incremental descent method for multi-objective optimization

Current state-of-the-art multi-objective optimization solvers, by comput...
research
01/24/2019

Multi-objective training of Generative Adversarial Networks with multiple discriminators

Recent literature has demonstrated promising results for training Genera...
research
10/12/2022

Optimizing Evaluation Metrics for Multi-Task Learning via the Alternating Direction Method of Multipliers

Multi-task learning (MTL) aims to improve the generalization performance...
research
11/08/2019

Penalty Method for Inversion-Free Deep Bilevel Optimization

Bilevel optimizations are at the center of several important machine lea...
research
03/24/2011

Design and classification of dynamic multi-objective optimization problems

In this work we provide a formal model for the different time-dependent ...
research
02/05/2022

A bird's eye view on Multi-Objective Optimization techniques in Relational Databases

Multi-objective optimization is the problem of optimizing simultaneously...

Please sign up or login with your details

Forgot password? Click here to reset