diff options
| author | Yuren Hao <yurenh2@illinois.edu> | 2026-07-09 10:42:11 -0500 |
|---|---|---|
| committer | Yuren Hao <yurenh2@illinois.edu> | 2026-07-09 10:42:11 -0500 |
| commit | 813447e9f14d62b2c1c8d8adae6eeb882c0a2eed (patch) | |
| tree | 317eee66ffb5399790affe08a884d128d64313a4 /docs/campaign/FINDINGS.md | |
| parent | fa50d50dc6ee53cf917276e4ca1770f451312124 (diff) | |
FINDINGS: final C1 verdict — equilibrium fb-EP 2.2949 beats BP 2.3694 (same init/seed/steps), cos 1.0000 throughout, 3.9x BP cost
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_014FAPDWQ49M5Ye3NpTndTpn
Diffstat (limited to 'docs/campaign/FINDINGS.md')
| -rw-r--r-- | docs/campaign/FINDINGS.md | 10 |
1 files changed, 8 insertions, 2 deletions
diff --git a/docs/campaign/FINDINGS.md b/docs/campaign/FINDINGS.md index 6ab1339..d3da6bb 100644 --- a/docs/campaign/FINDINGS.md +++ b/docs/campaign/FINDINGS.md @@ -721,8 +721,14 @@ nudge +β·CE at the top, relax states to the nudged equilibrium, ∇θ = local **Result (diagC, tied + 0.02 init, equilibrium fb-EP, NO regularizers, NO guards triggered): best val CE 2.9021 in 1500 steps, cos(EP,BP) pinned at 1.0000 throughout, K=3 never raised** — -already below the bad-init BP twin's 4000-step 2.9746. Final same-init C1 pair (casc_bp6i vs -casc_eqv5, 4k steps) running. +already below the bad-init BP twin's 4000-step 2.9746. + +**FINAL C1 VERDICT (same-init pair, 4k steps, seed 0): equilibrium fb-EP 2.2949 vs BP 2.3694 — +EP BEATS BP by 0.074** (cos pinned 1.0000 the whole run, zero skips, K=3 never raised, wall-clock +3.9× BP: 2.23 vs 8.79 it/s on the same 1080). K1 (exactness-on-trajectory), K2 (GPU cost), and K3 +(training parity, exceeded) are all bought. Same EP>BP flavor as the looped-EP 1.7065-vs-1.7921 +flagship — second independent instance of the pattern. Remaining: K4 depth rungs (L12 C512, D-tier) +and K5 analog tolerances (E-tier). **Costs & implications:** equilibrium-mode ≈ 4× BP (fb K3 single-sided) ⟹ $20k AWS ≈ 3–4B-param Chinchilla run in TRUE-EP mode. Optimization headroom mapped (±phase batching, red-black grouped |