summaryrefslogtreecommitdiff
path: root/models/srm
AgeCommit message (Collapse)Author
16 hoursSRM-AOL: codex review fixesYurenHao0426
- Soften exact Lipschitz claim — bf16 cast makes bound approximate (only exact in fp32) - BlockGain init_diag 1.0 → 3.0: original gave 27% cross-coupling (mislabeled "minimal"); 3.0 gives ~5% which is what "minimal" should mean - Note torch.compile risk with linalg.solve in CayleyOrthogonal Per codex review of v1. Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
16 hoursAdd SRM-Joint-AOL v1 modelYurenHao0426
Forked from HRM ACT framework. Replaces dual H_level/L_level transformer stacks with a single joint operator T(h, l) that is provably contractive under weighted P-norm with Lip_P(T) ≤ (1-α) + α·κ < 1. Per-step Lyapunov bound: λ_1 ≤ log((1-α) + α·κ). With κ=0.86 → λ_1 ≤ -0.15 ≈ HRM success regime (no CF needed). Components: - AOLLinear: 1-Lipschitz via Prach & Lampert rescaling (float32 normalization) - AOLBlock: stack with ReLU (1-Lipschitz activation) - CayleyOrthogonal: exact orthogonal cross-coupling - BlockGain: softmax row-sum bound under P-norm - AOLTokenMixer: 1-Lipschitz token + channel mixing Smoke test passes: params=939k (hidden=256 test config), forward OK, empirical Lip=0.17 < theoretical bound 0.90. Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>