From 2446bb758f6ec7456c1279e6b8ea5ebda9530cc3 Mon Sep 17 00:00:00 2001
From: YurenHao0426 <Blackhao0426@gmail.com>
Date: Thu, 28 May 2026 22:57:15 -0500
Subject: Add functional capacity overlap simulation

---
 scripts/functional_capacity_overlap.py | 298 +++++++++++++++++++++++++++++++++
 1 file changed, 298 insertions(+)
 create mode 100755 scripts/functional_capacity_overlap.py

(limited to 'scripts/functional_capacity_overlap.py')

diff --git a/scripts/functional_capacity_overlap.py b/scripts/functional_capacity_overlap.py
new file mode 100755
index 0000000..266f2ea
--- /dev/null
+++ b/scripts/functional_capacity_overlap.py
@@ -0,0 +1,298 @@
+#!/usr/bin/env python3
+"""Validate random-subspace functional capacity overlap formulas.
+
+Let S be a d-dimensional task-sensitive subspace in R^P and E be a k-dimensional
+alignment constraint subspace. For generic subspaces:
+
+  hard rank loss = max(0, k - (P - d))
+
+and the soft overlap T = tr(P_E P_S) satisfies:
+
+  E[T] = kd/P.
+"""
+
+from __future__ import annotations
+
+import argparse
+import csv
+import json
+from dataclasses import asdict, dataclass
+from pathlib import Path
+
+import matplotlib.pyplot as plt
+import numpy as np
+
+
+@dataclass(frozen=True)
+class RunConfig:
+    parameters: int
+    task_rank: int
+    constraint_ranks: list[int]
+    trials: int
+    seed: int
+    rank_tol: float
+    outdir: str
+    plot: bool
+
+
+@dataclass(frozen=True)
+class CapacityRow:
+    constraint_rank: int
+    hard_loss_empirical_mean: float
+    hard_loss_empirical_std: float
+    hard_loss_theory: float
+    soft_overlap_empirical_mean: float
+    soft_overlap_empirical_var: float
+    soft_overlap_theory_mean: float
+    soft_overlap_theory_var: float
+
+
+def parse_args() -> argparse.Namespace:
+    parser = argparse.ArgumentParser(
+        description="Validate redundancy-exhaustion capacity formulas."
+    )
+    parser.add_argument(
+        "--parameters",
+        type=int,
+        default=128,
+        help="Ambient parameter dimension P.",
+    )
+    parser.add_argument(
+        "--task-rank",
+        type=int,
+        default=32,
+        help="Task-sensitive subspace dimension d.",
+    )
+    parser.add_argument(
+        "--constraint-ranks",
+        type=int,
+        nargs="+",
+        default=[0, 16, 32, 64, 96, 112, 128],
+        help="Alignment constraint ranks k to test.",
+    )
+    parser.add_argument("--trials", type=int, default=200, help="Monte Carlo trials.")
+    parser.add_argument("--seed", type=int, default=0, help="Random seed.")
+    parser.add_argument(
+        "--rank-tol",
+        type=float,
+        default=1e-9,
+        help="Numerical tolerance for rank estimation.",
+    )
+    parser.add_argument(
+        "--outdir",
+        type=Path,
+        default=Path("outputs/functional_capacity_overlap"),
+        help="Output directory.",
+    )
+    parser.add_argument("--plot", action="store_true", help="Save plots.")
+    return parser.parse_args()
+
+
+def random_orthonormal(
+    rng: np.random.Generator, ambient_dim: int, subspace_dim: int
+) -> np.ndarray:
+    if subspace_dim == 0:
+        return np.empty((ambient_dim, 0), dtype=np.float64)
+    values = rng.standard_normal((ambient_dim, subspace_dim))
+    q, _ = np.linalg.qr(values, mode="reduced")
+    return q[:, :subspace_dim]
+
+
+def hard_rank_loss(
+    task_basis: np.ndarray, constraint_basis: np.ndarray, rank_tol: float
+) -> int:
+    task_rank = task_basis.shape[1]
+    if constraint_basis.shape[1] == 0:
+        return 0
+    projected = task_basis - constraint_basis @ (constraint_basis.T @ task_basis)
+    remaining_rank = np.linalg.matrix_rank(projected, tol=rank_tol)
+    return int(task_rank - remaining_rank)
+
+
+def soft_overlap(task_basis: np.ndarray, constraint_basis: np.ndarray) -> float:
+    if task_basis.shape[1] == 0 or constraint_basis.shape[1] == 0:
+        return 0.0
+    cross = constraint_basis.T @ task_basis
+    return float(np.sum(cross * cross))
+
+
+def theory_hard_loss(parameters: int, task_rank: int, constraint_rank: int) -> int:
+    return max(0, constraint_rank - (parameters - task_rank))
+
+
+def theory_soft_variance(parameters: int, task_rank: int, constraint_rank: int) -> float:
+    p = parameters
+    d = task_rank
+    k = constraint_rank
+    if p <= 2:
+        return 0.0
+    numerator = 2 * k * d * (p - k) * (p - d)
+    denominator = p * p * (p - 1) * (p + 2)
+    return numerator / denominator
+
+
+def run_trials(config: RunConfig) -> list[CapacityRow]:
+    rng = np.random.default_rng(config.seed)
+    rows: list[CapacityRow] = []
+
+    for constraint_rank in config.constraint_ranks:
+        hard_losses = np.empty(config.trials, dtype=np.float64)
+        overlaps = np.empty(config.trials, dtype=np.float64)
+
+        for trial in range(config.trials):
+            task_basis = random_orthonormal(
+                rng, config.parameters, config.task_rank
+            )
+            constraint_basis = random_orthonormal(
+                rng, config.parameters, constraint_rank
+            )
+            hard_losses[trial] = hard_rank_loss(
+                task_basis, constraint_basis, config.rank_tol
+            )
+            overlaps[trial] = soft_overlap(task_basis, constraint_basis)
+
+        rows.append(
+            CapacityRow(
+                constraint_rank=constraint_rank,
+                hard_loss_empirical_mean=float(np.mean(hard_losses)),
+                hard_loss_empirical_std=float(np.std(hard_losses, ddof=1))
+                if config.trials > 1
+                else 0.0,
+                hard_loss_theory=float(
+                    theory_hard_loss(
+                        config.parameters, config.task_rank, constraint_rank
+                    )
+                ),
+                soft_overlap_empirical_mean=float(np.mean(overlaps)),
+                soft_overlap_empirical_var=float(np.var(overlaps, ddof=1))
+                if config.trials > 1
+                else 0.0,
+                soft_overlap_theory_mean=constraint_rank
+                * config.task_rank
+                / config.parameters,
+                soft_overlap_theory_var=theory_soft_variance(
+                    config.parameters, config.task_rank, constraint_rank
+                ),
+            )
+        )
+
+    return rows
+
+
+def write_outputs(config: RunConfig, rows: list[CapacityRow], outdir: Path) -> None:
+    outdir.mkdir(parents=True, exist_ok=True)
+    payload = {
+        "config": asdict(config),
+        "rows": [asdict(row) for row in rows],
+    }
+    (outdir / "summary.json").write_text(
+        json.dumps(payload, indent=2, sort_keys=True) + "\n"
+    )
+
+    with (outdir / "summary.csv").open("w", newline="") as handle:
+        writer = csv.DictWriter(handle, fieldnames=list(asdict(rows[0]).keys()))
+        writer.writeheader()
+        for row in rows:
+            writer.writerow(asdict(row))
+
+
+def save_plots(rows: list[CapacityRow], outdir: Path) -> list[Path]:
+    outdir.mkdir(parents=True, exist_ok=True)
+    paths: list[Path] = []
+    k = np.array([row.constraint_rank for row in rows])
+
+    hard_path = outdir / "hard_rank_loss.png"
+    plt.figure(figsize=(7, 4.5))
+    plt.plot(
+        k,
+        [row.hard_loss_empirical_mean for row in rows],
+        marker="o",
+        label="empirical",
+    )
+    plt.plot(
+        k,
+        [row.hard_loss_theory for row in rows],
+        linestyle="--",
+        color="black",
+        label="theory",
+    )
+    plt.xlabel("constraint rank k")
+    plt.ylabel("hard functional rank loss")
+    plt.title("Redundancy-exhaustion transition")
+    plt.legend()
+    plt.tight_layout()
+    plt.savefig(hard_path, dpi=180)
+    plt.close()
+    paths.append(hard_path)
+
+    soft_path = outdir / "soft_overlap.png"
+    plt.figure(figsize=(7, 4.5))
+    plt.plot(
+        k,
+        [row.soft_overlap_empirical_mean for row in rows],
+        marker="o",
+        label="empirical mean",
+    )
+    plt.plot(
+        k,
+        [row.soft_overlap_theory_mean for row in rows],
+        linestyle="--",
+        color="black",
+        label="theory mean",
+    )
+    plt.xlabel("constraint rank k")
+    plt.ylabel("soft overlap tr(P_E P_S)")
+    plt.title("Soft functional capacity overlap")
+    plt.legend()
+    plt.tight_layout()
+    plt.savefig(soft_path, dpi=180)
+    plt.close()
+    paths.append(soft_path)
+
+    return paths
+
+
+def main() -> None:
+    args = parse_args()
+    if args.parameters < 1:
+        raise ValueError("--parameters must be positive.")
+    if not 0 <= args.task_rank <= args.parameters:
+        raise ValueError("--task-rank must be in [0, parameters].")
+    if any(k < 0 or k > args.parameters for k in args.constraint_ranks):
+        raise ValueError("All constraint ranks must be in [0, parameters].")
+    if args.trials < 1:
+        raise ValueError("--trials must be positive.")
+
+    config = RunConfig(
+        parameters=args.parameters,
+        task_rank=args.task_rank,
+        constraint_ranks=args.constraint_ranks,
+        trials=args.trials,
+        seed=args.seed,
+        rank_tol=args.rank_tol,
+        outdir=str(args.outdir),
+        plot=args.plot,
+    )
+
+    rows = run_trials(config)
+    write_outputs(config, rows, args.outdir)
+    plot_paths = save_plots(rows, args.outdir) if args.plot else []
+
+    print(f"parameters P: {args.parameters}")
+    print(f"task rank d: {args.task_rank}")
+    print(f"trials: {args.trials}")
+    print(f"table: {args.outdir / 'summary.csv'}")
+    for row in rows:
+        print(
+            f"k={row.constraint_rank}: "
+            f"hard={row.hard_loss_empirical_mean:.6g} "
+            f"(theory {row.hard_loss_theory:.6g}), "
+            f"soft={row.soft_overlap_empirical_mean:.6g} "
+            f"(theory {row.soft_overlap_theory_mean:.6g})"
+        )
+    for path in plot_paths:
+        print(f"plot: {path}")
+
+
+if __name__ == "__main__":
+    main()
-- 
cgit v1.2.3