Classification on SATIMAGE
0.132Empirical RiskAlg. 1
Evaluation results
| Method | Links | ||
|---|---|---|---|
| Alg. 1model=Neural Network, epsilon (ε)=1/m, K=0.2√m2023.06 | 0.132 | 0.184 | |
| Alg. 1Model=Neural Network, Learning mode=Batch, epsilon=1/m2023.06 | 0.132 | 0.184 | |
| Alg. 1Model Type=Linear, Learning Setting=Batch, epsilon=1/√m, K=0.2√m2023.06 | 0.138 | 0.201 | |
| ERMmodel=Neural Network2023.06 | 0.141 | 0.189 | |
| ERMModel=Neural Network, Learning mode=Batch2023.06 | 0.141 | 0.189 | |
| Alg. 1Model Type=Linear, Learning Setting=Batch, epsilon=1/m, K=0.2√m2023.06 | 0.144 | 0.2 | |
| ERMModel Type=Linear, Learning Setting=Batch2023.06 | 0.148 | 0.209 | |
| Alg. 1model=Neural Network, epsilon (ε)=1/√m, K=0.2√m2023.06 | 0.149 | 0.172 | |
| Alg. 1Model=Neural Network, Learning mode=Batch, epsilon=1/sqrt(m)2023.06 | 0.149 | 0.172 | |
| OGDModel architecture=Linear model, Learning protocol=Online learning2023.06 | 0.635 | 0.888 | |
| Alg. 2Model architecture=Linear model, Learning protocol=Online learning2023.06 | 0.669 | 0.938 |