High-dimensional SGD aligns with emerging outlier eigenspaces.
Gérard Ben ArousReza GheissariJiaoyang HuangAukosh JagannathPublished in: CoRR (2023)
Keyphrases
- high dimensional
- nearest neighbor search
- outlier detection
- high dimensionality
- low dimensional
- similarity search
- high dimensional data
- nearest neighbor
- dimensionality reduction
- multi modal
- variable selection
- high dimensional datasets
- sparse data
- feature space
- microarray data
- stochastic gradient descent
- metric space
- image pairs
- neural network
- data points
- data mining
- sparse coding
- high dimensional spaces
- data sets
- high dimensional problems