Multiclass classification by sparse multinomial logistic regression
share
In this paper we consider high-dimensional multiclass classification by sparse multinomial logistic regression extending the results of Abramovich and Grinshtein (2019) for the binary case. We propose a feature selection procedure based on penalized maximum likelihood with a complexity penalty on the model size and derive the nonasymptotic bounds for misclassification excess risk of the resulting classifier. We establish also their tightness by deriving the corresponding minimax lower bounds. In particular, we show that there exist two regimes corresponding to small and large number of classes. The bounds can be reduced under the additional low noise condition. Implementation of any complexity penalty based procedure, however, requires a combinatorial search over all possible models. To find a feature selection procedure computationally feasible for high-dimensional data, we propose multinomial logistic group Lasso and Slope classifiers and show that they also achieve the optimal order in the minimax sense.
READ FULL TEXT