Every Parameter Matters: Ensuring the Convergence of Federated Learning with Dynamic Heterogeneous Models Reduction.
Hanhan ZhouTian LanGuru VenkataramaniWenbo DingPublished in: CoRR (2023)
Keyphrases
- learning models
- learning process
- learning systems
- machine learning algorithms
- accurate models
- learning tasks
- model selection
- knowledge acquisition
- learning algorithm
- dynamic environments
- learning problems
- neural nets
- distributed systems
- supervised learning
- prior knowledge
- complex systems
- statistical models
- genetic algorithm
- learning rules
- structured prediction
- latent variable models
- machine learning