Lottery Pools: Winning More by Interpolating Tickets without Increasing Training or Inference Cost.
Lu YinShiwei LiuMeng FangTianjin HuangVlado MenkovskiMykola PechenizkiyPublished in: CoRR (2022)
Keyphrases
- structured prediction
- training algorithm
- bayesian networks
- high cost
- belief networks
- training set
- special case
- inference engine
- machine learning
- total cost
- training process
- probabilistic inference
- expected cost
- training phase
- minimum cost
- bayesian inference
- cost sensitive
- training examples
- online learning
- object detection
- computational complexity
- web services