Structural Dictionary Learning based on Non-convex Surrogate of ℓ₂,₁ Norm for Classification

Recently, group sparse representation which is based on a hypothesis about correlation of coefficient variables has attracted much attention due to its effectiveness and robustness in dictionary learning. Traditional group sparse representation methods use ℓ₂,₁ norm to enforce the estimation of models with joint sparsity patterns, which often leads to over-punishment phenomenon. To solve this issue, we replace ℓ₂,₁ with non-convex surrogate of ℓ₂,₁, and give a general solver for the corresponding optimization algorithm. Experimental results confirm the effectiveness of our proposed method.