Greedy Pruning with Group Lasso Provably Generalizes for Matrix Sensing and Neural Networks with Quadratic Activations.
Nived Rajaraman DevvritAryan MokhtariKannan RamchandranPublished in: CoRR (2023)
Keyphrases
- group lasso
- neural network
- low rank
- variable selection
- regression model
- contingency tables
- efficient optimization
- multiple kernel learning
- multi task
- convex optimization
- feature selection
- multi label learning
- multi task learning
- linear combination
- matrix factorization
- regularization term
- singular value decomposition
- linear models
- pairwise
- objective function
- machine learning
- cross validation
- missing data
- high dimensional data
- model selection
- feature space
- data analysis