Multi-Objective Learning to Predict Pareto Fronts Using Hypervolume Maximization

02/08/2021
by   Timo M. Deist, et al.
0

Real-world problems are often multi-objective with decision-makers unable to specify a priori which trade-off between the conflicting objectives is preferable. Intuitively, building machine learning solutions in such cases would entail providing multiple predictions that span and uniformly cover the Pareto front of all optimal trade-off solutions. We propose a novel learning approach to estimate the Pareto front by maximizing the dominated hypervolume (HV) of the average loss vectors corresponding to a set of learners, leveraging established multi-objective optimization methods. In our approach, the set of learners are trained multi-objectively with a dynamic loss function, wherein each learner's losses are weighted by their HV maximizing gradients. Consequently, the learners get trained according to different trade-offs on the Pareto front, which otherwise is not guaranteed for fixed linear scalarizations or when optimizing for specific trade-offs per learner without knowing the shape of the Pareto front. Experiments on three different multi-objective tasks show that the outputs of the set of learners are indeed well-spread on the Pareto front. Further, the outputs corresponding to validation samples are also found to closely follow the trade-offs that were learned from training samples for our set of benchmark problems.

READ FULL TEXT

page 10

page 11

research
08/04/2023

Optimization on Pareto sets: On a theory of multi-objective optimization

In multi-objective optimization, a single decision vector must balance t...
research
08/29/2022

Generalization In Multi-Objective Machine Learning

Modern machine learning tasks often require considering not just one but...
research
12/02/2022

Improving Pareto Front Learning via Multi-Sample Hypernetworks

Pareto Front Learning (PFL) was recently introduced as an effective appr...
research
09/28/2022

Supervised Contrastive Learning as Multi-Objective Optimization for Fine-Tuning Large Pre-trained Language Models

Recently, Supervised Contrastive Learning (SCL) has been shown to achiev...
research
12/13/2022

Policy learning for many outcomes of interest: Combining optimal policy trees with multi-objective Bayesian optimisation

Methods for learning optimal policies use causal machine learning models...
research
09/05/2022

Multiobjective Ranking and Selection Using Stochastic Kriging

We consider multiobjective simulation optimization problems, where sever...
research
06/03/2015

Multi-Objective Optimization for Self-Adjusting Weighted Gradient in Machine Learning Tasks

Much of the focus in machine learning research is placed in creating new...

Please sign up or login with your details

Forgot password? Click here to reset