diff options
Diffstat (limited to 'RAIN_EP_DILLAVOU_MATRIX.md')
| -rw-r--r-- | RAIN_EP_DILLAVOU_MATRIX.md | 15 |
1 files changed, 13 insertions, 2 deletions
diff --git a/RAIN_EP_DILLAVOU_MATRIX.md b/RAIN_EP_DILLAVOU_MATRIX.md index 8e1b0e3..3e8c30d 100644 --- a/RAIN_EP_DILLAVOU_MATRIX.md +++ b/RAIN_EP_DILLAVOU_MATRIX.md @@ -33,7 +33,7 @@ coincide. A difference between them is neither predicted nor claimed. - FashionMNIST with the author's 32x32 augmentation; - author ConvHopfieldEnergy32 architecture, gains and per-layer rates; - beta 0.25, 15 training relaxation iterations, 60 inference iterations; -- batch size 100 and 100-epoch cosine schedule. +- batch size 128 and 100-epoch cosine schedule. ## S0 development screen @@ -41,7 +41,8 @@ S0 uses only a fixed training/holdout split with 10,000 training and 2,000 holdout examples. One epoch selects a non-catastrophic offset magnitude from the frozen grid `0.003, 0.01, 0.03, 0.1`. The same wave includes clean PEP, random-sign beta, centered EP, and one SDIL arm. S0 is development evidence -and is never reported as a final result. +and is never reported as a final result. S0 and S0b used batch size 100, not +the author's batch size 128. S0 did not select a magnitude. Clean PEP reached 57.55% holdout accuracy, while raw offsets from 0.003 through 0.1 reached 60.0--61.8%. At this short @@ -67,6 +68,16 @@ The stronger-beta proxy was non-monotonic: beta 0.5 reached 54.40%, beta 1.0 reached 8.50%, and beta 2.0 became nonfinite. These are one-seed, one-epoch development observations, not confirmation results. +## C0 full-data trajectory check + +C0 freezes ratio 1.0 before launch and returns to the exact author data and +batch protocol: all 60,000 FashionMNIST training examples, the 10,000-example +test set, batch size 128, and the first 10 epochs of the unchanged 100-epoch +cosine schedule. One seed runs eight cells: positive EP clean/raw/constant/ +SDIL, random-sign clean/raw, and centered clean/raw. C0 checks whether the S0b +separation persists beyond a small development subset. It is still not the +multi-seed 100-epoch confirmation. + ## Confirmation matrix After S0 freezes one offset magnitude, the full author horizon compares: |