Multimodal Distribution Matching on Moons synthetic landscape
0.0002L1 Distance (Last Epoch)Boosted GFlowNet (2 models, flow-additive)
Evaluation results
| Method | Links | |
|---|---|---|
| Boosted GFlowNet (2 models, flow-additive)Noise level (epsilon)=0, Sample size (n)=62025.11 | 0.0002 | |
| Boosted GFlowNet (2 models, flow-additive)Noise level (epsilon)=0.1, Sample size (n)=62025.11 | 0.0002 | |
| Boosted GFlowNet (3 models, flow-additive)Noise level (epsilon)=0, Sample size (n)=62025.11 | 0.0002 | |
| Boosted GFlowNet (3 models, flow-additive)Noise level (epsilon)=0.1, Sample size (n)=62025.11 | 0.0002 | |
| Boosted GFlowNet (2 models, flow-additive)Noise level (epsilon)=0.2, Sample size (n)=62025.11 | 0.0003 | |
| Boosted GFlowNet (3 models, flow-additive)Noise level (epsilon)=0.5, Sample size (n)=62025.11 | 0.0003 | |
| Boosted GFlowNet (3 models, flow-additive)Noise level (epsilon)=0.3, Sample size (n)=62025.11 | 0.0003 | |
| Boosted GFlowNet (3 models, flow-additive)Noise level (epsilon)=0.2, Sample size (n)=62025.11 | 0.0004 | |
| Boosted GFlowNet (3 models, flow-additive)Noise level (epsilon)=0.4, Sample size (n)=62025.11 | 0.0004 | |
| Boosted GFlowNet (2 models, flow-additive)Noise level (epsilon)=0.3, Sample size (n)=62025.11 | 0.0004 | |
| Boosted GFlowNet (2 models, flow-additive)Noise level (epsilon)=0.5, Sample size (n)=62025.11 | 0.0006 | |
| Boosted GFlowNet (2 models, flow-additive)Noise level (epsilon)=0.4, Sample size (n)=62025.11 | 0.0006 | |
| Single GFlowNetNoise level (epsilon)=0.2, Sample size (n)=62025.11 | 0.001 | |
| Single GFlowNetNoise level (epsilon)=0, Sample size (n)=62025.11 | 0.001 | |
| Single GFlowNetNoise level (epsilon)=0.1, Sample size (n)=62025.11 | 0.001 | |
| Single GFlowNetNoise level (epsilon)=0.3, Sample size (n)=62025.11 | 0.0011 | |
| Single GFlowNetNoise level (epsilon)=0.4, Sample size (n)=62025.11 | 0.0011 | |
| Single GFlowNetNoise level (epsilon)=0.5, Sample size (n)=62025.11 | 0.0012 |