============================================================================== MIMO retrieval/interpolation baselines ============================================================================== [mimo plants] seeds: 9999 [mimo diffusion] seeds: (0, 1, 2) /home/cercola/matte_server/DiffusionControl/nonlinear/data_generation/mimo_lmi.py:29: UserWarning: Solution may be inaccurate. Try another solver, adjusting the solver settings, or solve with verbose=True for more information. prob.solve(solver=cp.SCS, verbose=False) computing MIMO oracle (150-step batched Adam, arm-independent, N=120)... oracle: 1900.0 ms/plant diffusion generation: 38.18 ms/controller (mean over 3 seeds) === MIMO retrieval/interpolation baselines (N=120, seed=9999) === verifier: simulate_closed_loop_mimo_batched rollout (n_ic=4, dt=0.03, duration=12.0, energy_thresh=0.3) oracle: eval_mimo_regret.py's oracle protocol (fixed generic init 0.3*cap, 150-step batched Adam lr=0.08 through the differentiable MIMO sim, sector-projected) -- arm-independent, computed ONCE, shared by every arm (1900.0 ms/plant) K_std=8, diffusion seeds=(0, 1, 2) --- K=8 --- arm coverage persamp reg_med% reg_p90% reg_max% ms/plant McNemar(n10,n01,p) Wilcoxon(n,p) diffusion 1.00 0.95 2.32 8.89 31.76 305.42 (reference) (reference) (sd across 3 seeds: coverage 0.004, per-samp 0.004) retrieval 0.99 0.92 2.62 11.04 33.89 1.165 (0,1,1) (119,0.87) interpolation 0.99 0.93 2.86 12.50 36.31 1.165 (0,1,1) (119,0.89) --- K=1 --- arm coverage persamp reg_med% reg_p90% reg_max% ms/plant McNemar(n10,n01,p) Wilcoxon(n,p) diffusion 0.94 0.94 9.83 70.78 819.17 305.42 (reference) (reference) (sd across 3 seeds: coverage 0.004, per-samp 0.004) retrieval 0.86 0.86 13.66 96.49 496.91 0.338 (0,10,0.002) (103,0.17) interpolation 0.86 0.86 13.66 96.49 496.91 0.338 (0,10,0.002) (103,0.17)