Fixed-Penalty Linearized Augmented-Lagrangian Training / reference implementation
Mechanism confirmed, baseline not beaten
Fixed-Penalty Linearized Augmented-Lagrangian Training — reference implementation
Runnable experiment code, benchmark implementation, machine-readable results and reports for this SynthCore idea.
Language: Python · Runtime: Python 3 · License: MIT
Public artifacts
bench_report.json— 3.4 KBbench_run.py— 6.6 KBexperiment.py— 6.4 KBreport.md— 1.5 KBreport_bench_2026-09-01T175207.md— 5.0 KBresults.json— 20.9 KB