# Image Classification on MNIST non-i.i.d. partitioning Dirichlet alpha=0.5 Regular graph (test)

Source: [Image Classification on MNIST non-i.i.d. partitioning Dirichlet alpha=0.5 Regular graph (test)](<https://www.sota2.com/research/sota/image-classification-on-mnist-non-i-i-d-partitioning-dirichlet-alpha-0-5-regular-graph-test>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-04-16T07:03:06.197Z

Evaluation of Image Classification performance on the MNIST test set partitioned using a non-i.i.d. Dirichlet distribution with alpha=0.5, structured according to a Regular graph.

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

| Scope | Recorded value |
| --- | --- |
| Task | Image Classification |
| Dataset (including any stated split) | MNIST non-i.i.d. partitioning Dirichlet alpha=0.5 Regular graph (test) |
| Metric | Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 4 of 4 |
| Coverage | All results currently returned for this benchmark |

Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol.

## Metrics

- [Accuracy](<https://www.sota2.com/research/sota/image-classification-on-mnist-non-i-i-d-partitioning-dirichlet-alpha-0-5-regular-graph-test.md?metric=Accuracy>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| A single SGD, no Pac-Man | 97.19 | Not recorded | 68fa7aaf1e209131cea849d0 |
| AC | 96.11 | Not recorded | 68fa7aaf1e209131cea849d0 |
| DeCaFork | 96.06 | Not recorded | 68fa7aaf1e209131cea849d0 |
| A single SGD, no self-duplication | 51.66 | Not recorded | 68fa7aaf1e209131cea849d0 |

### A single SGD, no Pac-Man

Accuracy: 97.19. Result ID: 69e0881e47f34ce924c9433b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7aaf1e209131cea849d0.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### AC

Accuracy: 96.11. Result ID: 69e0881e47f34ce924c9433c.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7aaf1e209131cea849d0.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7aaf1e209131cea849d0.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### DeCaFork

Accuracy: 96.06. Result ID: 69e0881e47f34ce924c9433d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7aaf1e209131cea849d0.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### A single SGD, no self-duplication

Accuracy: 51.66. Result ID: 69e0881e47f34ce924c9433e.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7aaf1e209131cea849d0.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

Page 1 of 1. This is an index page, not the full collection.
