Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

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.

Fengbei Liu, Rachit Saluja, Sunwoo Kwak, Ruibo Wang, Ruining Deng, Heejong Kim, Johannes C. Paetzold, Mert R. Sabuncu• 2026

Related benchmarks

TaskDatasetResultRank
Depth EstimationNYU V2--
207
Surface Normal PredictionNYU V2
Mean Error25.56
137
Semantic segmentationCityscapes
Mean IoU71.34
88
Depth EstimationCityscapes
Abs Err0.014
14
Semantic segmentationNYU V2
mIoU38.32
14
Multi-task LearningSARCOS 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 solvingPINNACLE
Error (1D Burgers, C)0.0129
6
PDE solvingPINNacle v1 (test)
Burgers 1D (C) Error0.0148
6
Showing 10 of 11 rows

Other info

Follow for update