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

Posted in Papers

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.

I am PhD student at Skolkovo Institute of Science and Technology and Senior Lecturer at Moscow Institute of Physics and Technology. I love math, teaching, history, travelling and the ambiguity of being.

Read Next

Stochastic gradient algorithms from ODE splitting perspective