Phase 40-4a · head classifier

Postnet × Cloudflare — federated AG News head classifier

Federated training of a 2-layer MLP head (D=384 → H=128 → K=4, P = 49 796) on pre-computed MiniLM-L6-v2 features for 4-class AG News topic classification (World / Sports / Business / Sci-Tech). The features are baked into a 154 KB static asset (/data/agnews-mini.bin) — no MiniLM inference in the browser. Each tab is a federated SPSA worker; the server uses Phase 39's symmetric AIMD adaptive η.

↑0 B ↓0 B
test loss test accuracy
(idle)

Protocol: SPSA tournament (DeComFL fusion, Phase 36+). Each round, this worker runs 4 SPSA trials on its private slice of 25 training examples; submits the trial with the most-negative claimed Δloss as a 20-byte proposal (seed, scalar_g, delta). Server picks the best across all workers, applies θ ← θ − η · g · u(seed), broadcasts the applied flip. Adaptive η: server uses Phase 39's symmetric AIMD — η ← η × 1.05 on a real loss drop, ← η × 1/1.05 on a regression, computed from the server's own test-set forward pass on the 25 held-out examples.

Federation: 3 disjoint training shards (25 examples each). Your shard is fixed by the hash of your worker id. With 3+ joined peers the swarm covers all training data; the server scores on the shared test set (the byzantine truth).