chore: capture initial SDIL project state

1 files changed, 86 insertions, 0 deletions

diff --git a/experiments/smoke.py b/experiments/smoke.py
new file mode 100644
index 0000000..f2efa87
--- /dev/null
+++ b/experiments/smoke.py
@@ -0,0 +1,86 @@
+"""Fast CPU correctness checks for SDIL mechanics and signs.
+Run: python experiments/smoke.py
+"""
+import os
+import sys
+import torch
+
+sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
+from sdil.core import SDILNet, SDILConfig, sdil_step, node_perturbation_targets
+from sdil.baselines import dfa_config
+from sdil import probes
+from sdil.data import get_dataset, onehot
+
+
+def row_cos(u, v, eps=1e-12):
+    return ((u * v).sum(1) / (u.norm(dim=1) * v.norm(dim=1) + eps)).mean().item()
+
+
+def main():
+    torch.manual_seed(0)
+    dev = "cpu"
+    print("loading MNIST subset...")
+    tr, te, n_in, n_out = get_dataset("mnist", batch_size=128, device=dev)
+    xb, yb = next(iter(tr))
+    x = xb[:256]
+    y = yb[:256]
+    yoh = onehot(y, 10)
+
+    sizes = [784, 64, 64, 64, 10]
+
+    # ---- CHECK 1: node-perturbation q estimates the descent direction -g ----
+    net = SDILNet(sizes, device=dev, seed=1)
+    grads, _ = probes.true_hidden_grads(net, x, y)
+    for ndirs in (1, 8, 32):
+        qs = node_perturbation_targets(net, x, y, sigma=1e-2, n_dirs=ndirs)
+        cs = [row_cos(qs[l], -grads[l]) for l in range(len(qs))]
+        print(f"CHECK1 node-pert n_dirs={ndirs:2d}  cos(q,-g) per layer = "
+              + " ".join(f"{c:+.3f}" for c in cs))
+    assert all(c > 0 for c in cs), "node perturbation q should align with -grad"
+
+    # ---- CHECK 2: SDIL overfits a fixed batch and alignment climbs ----
+    net = SDILNet(sizes, device=dev, seed=2)
+    cfg = SDILConfig(eta=0.1, eta_A=0.05, eta_P=0.005, pert_every=2, pert_ndirs=8,
+                     momentum=0.9)
+    print("\nCHECK2 SDIL overfit fixed batch:")
+    for step in range(401):
+        loss, _ = sdil_step(net, x, y, yoh, cfg, step)
+        if step % 50 == 0:
+            al = probes.alignment_report(net, x, y, yoh, cfg)
+            mc = sum(al["cos_r_negg"]) / len(al["cos_r_negg"])
+            mca = sum(al["cos_apical_negg"]) / len(al["cos_apical_negg"])
+            print(f"  step {step:3d} loss {loss:.4f} mean_cos(r,-g) {mc:+.3f} "
+                  f"mean_cos(apical,-g) {mca:+.3f} per-layer_r {['%.2f'%v for v in al['cos_r_negg']]}")
+    assert loss < 1.5, f"SDIL should reduce loss on fixed batch, got {loss}"
+
+    # ---- CHECK 3: trained-A SDIL beats fixed-random-A (DFA) on alignment ----
+    print("\nCHECK3 alignment: SDIL(trained A) vs DFA(fixed A):")
+    net_dfa = SDILNet(sizes, device=dev, seed=3)
+    cfg_dfa = dfa_config(eta=0.1, momentum=0.9)
+    for step in range(401):
+        sdil_step(net_dfa, x, y, yoh, cfg_dfa, step)
+    al_dfa = probes.alignment_report(net_dfa, x, y, yoh, cfg_dfa)
+    al_sdil = probes.alignment_report(net, x, y, yoh, cfg)
+    print(f"  DFA  mean_cos(r,-g) = {sum(al_dfa['cos_r_negg'])/len(al_dfa['cos_r_negg']):+.3f}")
+    print(f"  SDIL mean_cos(r,-g) = {sum(al_sdil['cos_r_negg'])/len(al_sdil['cos_r_negg']):+.3f}")
+
+    # ---- CHECK 4: nuisance -> residual preserves alignment, raw apical degrades ----
+    print("\nCHECK4 residualization under soma-predictable nuisance (rho=2.0):")
+    net_n = SDILNet(sizes, device=dev, seed=4, nuis_rho=2.0)
+    cfg_n = SDILConfig(eta=0.1, eta_A=0.05, eta_P=0.02, pert_every=2, pert_ndirs=8, momentum=0.9)
+    for step in range(401):
+        sdil_step(net_n, x, y, yoh, cfg_n, step)
+    al_n = probes.alignment_report(net_n, x, y, yoh, cfg_n)
+    print(f"  residual cos(r,-g)      = {sum(al_n['cos_r_negg'])/len(al_n['cos_r_negg']):+.3f}")
+    print(f"  raw apical cos(a,-g)    = {sum(al_n['cos_apical_negg'])/len(al_n['cos_apical_negg']):+.3f}")
+    print(f"  pure A c   cos(Ac,-g)   = {sum(al_n['cos_Ac_negg'])/len(al_n['cos_Ac_negg']):+.3f}")
+
+    # ---- CHECK 5: single-step loss-decrease ratio vs exact GD ----
+    print("\nCHECK5 single-step loss-decrease ratio vs exact GD:")
+    ldr = probes.loss_decrease_ratio(net, x, y, yoh, cfg, step=100)
+    print(f"  dL_sdil={ldr['dL_sdil']:+.4f} dL_bp={ldr['dL_bp']:+.4f} ratio={ldr['ratio']:+.3f}")
+    print("\nALL SMOKE CHECKS PASSED")
+
+
+if __name__ == "__main__":
+    main()