Algorithm 1. ADMM for LMVSC-Sparse. |
Input: multi-view data the multi-view data samples, denoted by , , , and the numbers of clusters. Initialize: , , , , , , , stooping tolerance . Repeat: Step 1: Computing by (19). Step 2: Computing by (25). Step 3: Computing by (30). Step 4: Computing by . Step 5: Computing . Until or achieved maxim iteration number. Output . |