High-dimensional Asymptotics of Feature Learning: How One Gradient Step Improves the Representation.
Jimmy BaMurat A. ErdogduTaiji SuzukiZhichao WangDenny WuGreg YangPublished in: NeurIPS (2022)
Keyphrases
- high dimensional
- learning algorithm
- reinforcement learning
- learning process
- learning systems
- supervised learning
- nearest neighbor
- similarity search
- sufficient conditions
- active learning
- semi supervised
- neural network
- mobile robot
- dimensionality reduction
- markov chain
- post processing
- high dimensional data
- object recognition
- feature selection
- learning problems