Sparse + Group-Sparse Dirty Models: Statistical Guarantees without Unreasonable Conditions and a Case for Non-Convexity.
Eunho YangAurélie C. LozanoPublished in: ICML (2017)
Keyphrases
- statistical models
- sparse data
- high dimensional
- information theoretic
- sparse matrix
- parameter estimation
- probabilistic model
- statistical analysis
- model selection
- complex systems
- prior knowledge
- statistical methods
- sparse coding
- dictionary learning
- social networks
- compressive sensing
- canonical correlation analysis
- statistical approaches
- goodness of fit
- theoretical guarantees
- learning algorithm