Repetita Iuvant: Data Repetition Allows SGD to Learn High-Dimensional Multi-Index Functions.
Luca ArnaboldiYatin DandiFlorent KrzakalaLuca PesceLudovic StephanPublished in: CoRR (2024)
Keyphrases
- data sets
- high dimensional
- synthetic data
- database
- data analysis
- data processing
- high dimensional data
- data points
- data distribution
- noisy data
- data sources
- sparse data
- end users
- original data
- multi dimensional
- data quality
- computer systems
- statistical analysis
- machine learning
- raw data
- high dimensionality
- dimensional data
- microarray
- low dimensional
- semi supervised
- image data
- knowledge discovery
- prior knowledge
- feature space
- databases