vvsandClaude Opus 5
de90c7a089
What the tables' totals hid: problem by problem the scheduled projection beats Chandrupatla on APS 87/24/42, exact sign test p = 9e-5, while trailing by 0.7% in total; on CHA Chandrupatla is genuinely better (26 to 9, p = 0.006). The earned projection ties him on APS problems (79/3/71, p = 0.57). Benchmark not yet switched to the library baseline - awaiting Valeri's decision together with the framing of the proposed method. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
62 lines
2.6 KiB
Python
62 lines
2.6 KiB
Python
"""Can the Chandrupatla baseline be the library alone? (Valeri, 2026-09-21)
|
|
|
|
Our own implementation stopped on a bracket twice as wide as everyone else's, and
|
|
best_of let that leak into the reported numbers. SciPy ships the method twice: the
|
|
private _chandrupatla, already in the benchmark, and the PUBLIC
|
|
scipy.optimize.elementwise.find_root (Chandrupatla's algorithm, SciPy >= 1.15). A
|
|
private function can change without notice, so the public one is the candidate; this
|
|
checks, problem by problem, that it spends exactly what the private one spends and
|
|
what our implementation spends once its tolerance is corrected.
|
|
|
|
python -u audit_chandrupatla_library.py
|
|
"""
|
|
from __future__ import annotations
|
|
|
|
import numpy as np
|
|
|
|
from audit_chandrupatla_tolerance import ours_half
|
|
from simroot.baselines import Counter, _Budget, chandrupatla_scipy
|
|
from stage12_validation import load, per_problem, totals
|
|
|
|
|
|
def chandrupatla_public(f, a, b, xtol, maxfev):
|
|
"""scipy.optimize.elementwise.find_root with the benchmark's stopping rule: bracket
|
|
narrower than xtol, relative term at machine precision, no stopping on |f|."""
|
|
from scipy.optimize import elementwise
|
|
g = Counter(f, maxfev)
|
|
|
|
def vec(x):
|
|
return np.asarray([g(float(xi)) for xi in np.atleast_1d(x)]).reshape(np.shape(x))
|
|
|
|
try:
|
|
res = elementwise.find_root(vec, (a, b), maxiter=maxfev,
|
|
tolerances=dict(xatol=xtol, xrtol=8.9e-16,
|
|
fatol=0.0, frtol=0.0))
|
|
return (float(np.asarray(res.x).ravel()[0]), g.n,
|
|
bool(np.all(np.asarray(res.success))))
|
|
except _Budget:
|
|
return 0.5 * (a + b), g.n, False
|
|
except Exception:
|
|
return 0.5 * (a + b), g.n, False
|
|
|
|
|
|
def main():
|
|
probs = load()
|
|
pub = per_problem(chandrupatla_public, probs, 200)
|
|
prv = per_problem(chandrupatla_scipy, probs, 200)
|
|
own = per_problem(ours_half, probs, 200)
|
|
for name, p in (("public find_root", pub), ("private _chandrupatla", prv),
|
|
("ours, tolerance corrected", own)):
|
|
t, ok = totals(p, probs)
|
|
print(f"{name:<28} APS {t['APS']:5d} ({ok['APS']}/154) CHA {t['CHA']:5d} "
|
|
f"({ok['CHA']}/45) both {t['APS'] + t['CHA']}")
|
|
diff_prv = [pid for pid in pub if pub[pid] != prv[pid]]
|
|
diff_own = [pid for pid in pub if pub[pid] != own[pid]]
|
|
print(f"\nproblems where public != private: {len(diff_prv)} {diff_prv[:8]}")
|
|
print(f"problems where public != ours corrected: {len(diff_own)} {diff_own[:8]}")
|
|
return {"pub": totals(pub, probs), "diff_prv": diff_prv, "diff_own": diff_own}
|
|
|
|
|
|
if __name__ == "__main__":
|
|
main()
|