Re-embedding data to strengthen recovery guarantees of clustering.
Tao JiangSamuel TanStephen A. VavasisPublished in: CoRR (2023)
Keyphrases
- data sets
- original data
- data distribution
- data points
- data collection
- raw data
- data analysis
- synthetic data
- high dimensional data
- computer systems
- input data
- prior knowledge
- data structure
- clustering algorithm
- spectral clustering
- categorical data
- k means
- high quality
- knowledge discovery
- image data
- data processing
- multidimensional data
- database
- data mining tasks
- sensor data
- multidimensional scaling
- missing data
- statistical analysis
- principal component analysis
- end users
- training data
- feature selection
- learning algorithm
- data mining
- neural network
- databases