Multi-Task Optimization in Neural Networks: Theory and Practice
Scalarization, learnable loss weights, gradient surgery, Pareto frontiers, and why nothing can beat mathematical theory
Welcome to this week’s issue of Machine Learning Frontiers! Here are recent issues you may have missed:
Keep reading with a 7-day free trial
Subscribe to Machine Learning Frontiers to keep reading this post and get 7 days of free access to the full post archives.