Performance Optimization of Machine Learning Inference under Latency and Server Power Constraints.
Guoyu ChenXiaorui WangPublished in: ICDCS (2022)
Keyphrases
- machine learning
- constrained optimization
- low latency
- knowledge acquisition
- optimization algorithm
- optimization problems
- network latency
- learning algorithm
- constraint satisfaction
- artificial intelligence
- client server
- information extraction
- natural language processing
- web server
- optimization criteria
- computational intelligence
- response time
- probabilistic model
- computer vision
- data mining
- bayesian networks
- power consumption
- learning tasks
- machine learning algorithms
- belief networks
- text mining
- linear constraints
- text classification
- low overhead