X29 write-up: source commits
Browse files- docs/icml_r3_x29.md +2 -2
docs/icml_r3_x29.md
CHANGED
|
@@ -5,7 +5,7 @@ status: SISO (with CPU), MIMO spline setting (with CPU) and actuator step 3A com
|
|
| 5 |
claim: X29 (Matteo 2026-11-16, via dc_presentation and in the move-HPC session): "I need to have the final baseline comparison also for the spline methods". C+phi (the model generates the linear part and the spline phi, X28) gets the same baselines and KPIs as C-only (phi fixed: SISO sat_1, MIMO identity) in every setting of the deck v10 slides.
|
| 6 |
maps_to: deck v10 slides [35] [36] [37] [38] [73] (SISO); the three new MIMO spline-setting slides and [73]; [50] [51] [52] [84] [73] (actuator); summaries [54] [72] [77]. No paper edit until Matteo agrees the claim.
|
| 7 |
scripts: nonlinear/experiments/x29_siso.py (SISO kNN, twins, optimizer from the best sample, timing, report), nonlinear/mimo_unstable/x29_t2.py (MIMO spline setting on T2: kNN, twins, 48-start solver, Adam references, timing, report), nonlinear/mimo_unstable/x29_act.py (actuator 3A: composed-sector certificate, simulated X27 cost, optimizer, new directions, report, X27 rows and re-score)
|
| 8 |
-
artifacts: results/icml_r3/X29/{PREREG.md, PREREG_siso.md, PREREG_t2.md}; results/icml_r3/X29/siso/{report.txt, eqcheck.txt, eval/, refine/, timing/, timing_batched.json}; results/icml_r3/X29/t2/{report.txt, numbers.json, cpu_report.txt, timing_m2.json, timing_m3.json, knn_m*_{a,b}.npz, twin_*.npz, solver_m*.npz, ard_m2.npz}; results/icml_r3/X29/act/{selfcheck_*.json, report_3a_heldout_m*.txt, heldout_m*/, x27rows_*.npy, x27rescore_*.txt, x27rescore_*.json}; models/x29_twin_clS{,_s1,_s2}/, models/x29t/; HF matCercola18/DiffusionControl commits 8f92ad1d (SISO), d7d0258 (MIMO spline setting), 09f35d5 (actuator 3A)
|
| 9 |
---
|
| 10 |
|
| 11 |
# C+phi next to C-only with the same baselines and KPIs (X29)
|
|
@@ -195,4 +195,4 @@ SISO (`results/icml_r3/X29/siso/report.txt`, CPU section; seconds per plant on o
|
|
| 195 |
- The MIMO spline J*_T2 uses id and so3 labels only, so T2 regrets are not on the scale of the held-out X28 regrets.
|
| 196 |
- The SISO and MIMO timings ran on two different nodes (move-hpc-06-gpu and move-hpc-08-gpu, 8 cores and an NVIDIA L40S each), each with nothing else of this project running. Ratios are computed within one setting's timing job.
|
| 197 |
|
| 198 |
-
**Sources:** the PREREG and addenda in `results/icml_r3/X29/`; the report files named in each section; HF commits 8f92ad1d (SISO), d7d0258 (MIMO spline setting)
|
|
|
|
| 5 |
claim: X29 (Matteo 2026-11-16, via dc_presentation and in the move-HPC session): "I need to have the final baseline comparison also for the spline methods". C+phi (the model generates the linear part and the spline phi, X28) gets the same baselines and KPIs as C-only (phi fixed: SISO sat_1, MIMO identity) in every setting of the deck v10 slides.
|
| 6 |
maps_to: deck v10 slides [35] [36] [37] [38] [73] (SISO); the three new MIMO spline-setting slides and [73]; [50] [51] [52] [84] [73] (actuator); summaries [54] [72] [77]. No paper edit until Matteo agrees the claim.
|
| 7 |
scripts: nonlinear/experiments/x29_siso.py (SISO kNN, twins, optimizer from the best sample, timing, report), nonlinear/mimo_unstable/x29_t2.py (MIMO spline setting on T2: kNN, twins, 48-start solver, Adam references, timing, report), nonlinear/mimo_unstable/x29_act.py (actuator 3A: composed-sector certificate, simulated X27 cost, optimizer, new directions, report, X27 rows and re-score)
|
| 8 |
+
artifacts: results/icml_r3/X29/{PREREG.md, PREREG_siso.md, PREREG_t2.md}; results/icml_r3/X29/siso/{report.txt, eqcheck.txt, eval/, refine/, timing/, timing_batched.json}; results/icml_r3/X29/t2/{report.txt, numbers.json, cpu_report.txt, timing_m2.json, timing_m3.json, knn_m*_{a,b}.npz, twin_*.npz, solver_m*.npz, ard_m2.npz}; results/icml_r3/X29/act/{selfcheck_*.json, report_3a_heldout_m*.txt, heldout_m*/, x27rows_*.npy, x27rescore_*.txt, x27rescore_*.json}; models/x29_twin_clS{,_s1,_s2}/, models/x29t/; HF matCercola18/DiffusionControl commits 8f92ad1d (SISO), d7d0258 (MIMO spline setting), 09f35d5 (actuator 3A), 374b6ec (SISO CPU, X27 re-score in the X29 convention, this write-up); git branch icml-experiments 225e6cf
|
| 9 |
---
|
| 10 |
|
| 11 |
# C+phi next to C-only with the same baselines and KPIs (X29)
|
|
|
|
| 195 |
- The MIMO spline J*_T2 uses id and so3 labels only, so T2 regrets are not on the scale of the held-out X28 regrets.
|
| 196 |
- The SISO and MIMO timings ran on two different nodes (move-hpc-06-gpu and move-hpc-08-gpu, 8 cores and an NVIDIA L40S each), each with nothing else of this project running. Ratios are computed within one setting's timing job.
|
| 197 |
|
| 198 |
+
**Sources:** the PREREG and addenda in `results/icml_r3/X29/`; the report files named in each section; HF commits 8f92ad1d (SISO), d7d0258 (MIMO spline setting), 09f35d5 (actuator 3A) and 374b6ec (SISO CPU, X27 re-score, this write-up).
|