Beyond Least-Squares: Fast Rates for Regularized Empirical Risk Minimization through Self-Concordance.
Ulysse Marteau-FereyDmitrii OstrovskiiFrancis R. BachAlessandro RudiPublished in: COLT (2019)
Keyphrases
- least squares
- empirical risk minimization
- empirical risk
- statistical learning theory
- uniform convergence
- risk minimization
- vc dimension
- linear regression
- rates of convergence
- optical flow
- generalization bounds
- ls svm
- computationally tractable
- sufficient conditions
- linear classifiers
- fixed number
- feature selection
- learning theory
- decision function
- theoretical framework