Review
Open access
Aug 2026
Common Pitfalls to Avoid While Using Multiobjective Optimization in Machine Learning
The groundwork for MOO is established, focusing on well-known approaches such as the weighted sum method alongside more advanced techniques like the multiobjective gradient descent algorithm (MGDA), and it is demonstrated that difficulties can arise regardless of the specific MOO method used.
Junaid Akhter, P. Fährmann, Konstantin Sonntag et al.
· SIAM Review · 0 citations