Files
PSO/benchmark_results/pso_v5_deep_methods.csv
T
jung-geun 813433000a feat: modernize PSO and add convergence research
Migrate the package and examples to the tensor-native PyTorch implementation, add benchmark evidence, and add the guarded post-training convergence protocol with TensorBoard progress monitoring and hash-verified recovery.

Constraint: Preserve one-shot official-test sealing and auditable research artifacts

Rejected: Commit local .omc runs and downloaded datasets | multi-gigabyte runtime state is machine-local

Confidence: high

Scope-risk: broad

Not-tested: Production CUDA run on pieroot-server
2026-09-07 22:03:25 +09:00

322 B

1sectionmetricvalue
2protocolversionMNIST-PSO-RAW-V5 1.0.0
3pilotselected_dimensionfull
4single_modeltest_accuracy83.23
5single_modeltest_nll0.556332
6single_modeltest_brier0.253921
7single_modeltest_ece0.085242
8ensembletest_accuracy87.0
9ensembletest_nll0.535928
10ensemblepairwise_disagreement0.1585