MAdam: Metric-Aware Multi-Objective Adam
About
Multi-objective optimization (MOO) underlies many machine learning problems, yet MOO solvers across the loss-balancing, gradient-balancing, and Pareto-based families almost universally hand their reconciled directions to Adam~\cite{kingma2015adam}. We show this coupling introduces two systematic gaps between the solver's intent and the optimizer's execution. The first is a \emph{weighting mismatch}: Adam's second-moment denominator entangles the time-varying preference vector with gradient statistics, marginalizing the preference into a history average and collapsing distinct Pareto trade-offs toward a near-uniform mixture. The second is a \emph{geometric mismatch}: Adam's adaptive metric distorts the Euclidean geometry MOO solvers assume, turning aligned objectives into apparent conflicts. To resolve both jointly, we introduce \textbf{MAdam} (Metric-Aware Multi-Objective Adam), a drop-in wrapper that leaves both solver and optimizer unchanged. MAdam preconditions the reconciled direction by the preference-conditioned curvature of the scalarized objective; on this whitened input, Adam's second moment collapses to identity, so the realized update is governed by the preference-conditioned metric. Across multi-task learning, Pareto-front recovery, physics-informed neural networks, and medical imaging, MAdam consistently improves over Adam for every solver family.
Related benchmarks
| Task | Dataset | Result | Rank | |
|---|---|---|---|---|
| Depth Estimation | NYU V2 | -- | 207 | |
| Surface Normal Prediction | NYU V2 | Mean Error25.56 | 137 | |
| Semantic segmentation | Cityscapes | Mean IoU71.34 | 88 | |
| Depth Estimation | Cityscapes | Abs Err0.014 | 14 | |
| Semantic segmentation | NYU V2 | mIoU38.32 | 14 | |
| Multi-task Learning | SARCOS standard (test) | Average Error9.92 | 10 | |
| Multi-Task Learning (Attribute Prediction) | UTKFace | Age MAE8.28 | 10 | |
| Multi-Task Learning (Digit Classification) | MultiMNIST | Average Accuracy95.14 | 10 | |
| PDE solving | PINNACLE | Error (1D Burgers, C)0.0129 | 6 | |
| PDE solving | PINNacle v1 (test) | Burgers 1D (C) Error0.0148 | 6 |