@inproceedings{20300,
  abstract     = {Simultaneously addressing multiple objectives is becoming increasingly important in modern machine learning. At the same time, data is often high-dimensional and costly to label. For a single objective such as prediction risk, conventional regularization techniques are known to improve generalization when the data exhibits low-dimensional structure like sparsity. However, it is largely unexplored how to leverage this structure in the context of multi-objective learning (MOL) with multiple competing objectives. In this work, we discuss how the application of vanilla regularization approaches can fail, and propose a two-stage MOL framework that can successfully leverage low-dimensional structure. We demonstrate its effectiveness experimentally for multi-distribution learning and fairness-risk trade-offs.},
  author       = {Wegel, Tobias and Kovačević, Filip and Ţifrea, Alexandru and Yang, Fanny},
  booktitle    = {The 28th International Conference on Artificial Intelligence and Statistics},
  issn         = {2640-3498},
  location     = {Mai Khao, Thailand},
  pages        = {4591--4599},
  publisher    = {ML Research Press},
  title        = {{Learning Pareto manifolds in high dimensions: How can regularization help?}},
  volume       = {258},
  year         = {2025},
}