More is Better in Modern Machine Learning: when Infinite Overparameterization is Optimal and Overfitting is Obligatory.
James B. SimonDhruva KarkadaNikhil GhoshMikhail BelkinPublished in: CoRR (2023)
Keyphrases
- machine learning
- decision trees
- optimal design
- data mining
- machine learning and data mining
- machine learning methods
- knowledge acquisition
- learning algorithm
- machine learning approaches
- data analysis
- text mining
- learning systems
- model selection
- computational intelligence
- dynamic programming
- feature selection
- artificial intelligence
- neural network
- supervised learning
- text classification
- knowledge discovery
- machine learning algorithms
- special case
- artificial neural networks
- learning problems
- optimal control
- training data
- supervised machine learning