Login / Signup
MaxGNR: A Dynamic Weight Strategy via Maximizing Gradient-to-Noise Ratio for Multi-Task Learning.
Caoyun Fan
Wenqing Chen
Jidong Tian
Yitian Li
Hao He
Yaohui Jin
Published in:
CoRR (2023)
Keyphrases
</>
multi task learning
multi task
gaussian processes
multiple tasks
learning problems
high order
learning tasks
theoretical analysis
transfer learning
multitask learning
noise ratio
prior knowledge
learning models
learning algorithm
multi label image annotation