Why are Adaptive Methods Good for Attention Models?
Jingzhao ZhangSai Praneeth KarimireddyAndreas VeitSeungyeon KimSashank J. ReddiSanjiv KumarSuvrit SraPublished in: NeurIPS (2020)
Keyphrases
- statistical models
- preprocessing
- neural network
- computational cost
- experimental data
- mathematical models
- significant improvement
- linear regression
- predictive power
- data sets
- monte carlo simulation
- classification models
- statistical methods
- machine learning methods
- statistical model
- benchmark datasets
- maximum likelihood
- prior knowledge
- evolutionary algorithm
- social networks
- learning algorithm