Information-Theoretic Requirements for Gradient-Based

Information-Theoretic Requirements for Gradient-Based Task Affinity Estimation in Multi-Task Learning

Announce Type: replace Abstract: Multi-task learning shows strikingly inconsistent results -- sometimes joint training helps substantially, sometimes it actively harms performance -- yet the field lacks a principled framework for predicting these outcomes. We identify a fundamental but unstated assumption underlying gradient-based task analysis: tasks must share training instances for gradient conflicts to reveal genuine relationships. When tasks are measured on the same inputs, gradient...