Verify sparse-ball shell probabilities with radial controls

This commit is contained in:
2026-11-11 23:21:53 +08:00
parent 9e0e659287
commit e1514f4952
10 changed files with 4536 additions and 0 deletions
+22
View File
@@ -0,0 +1,22 @@
# 稀疏分布与高维壳:条件定理及反例
在同一外半径R下,若X在d维球内均匀分布,P(||X||<=aR)=a^d。若X均匀分布于嵌入该空间的k维子空间球,则概率为a^k。0<a<1、k<d时严格有a^k>a^d。
因此用户猜想在上述模型下成立。k仍很大时也有薄壳,只是由有效维度k决定,而非环境维度d。
| r/R | 128维均匀球(理论) | 16维子空间均匀球(理论) | 内部概率倍数 |
|---|---:|---:|---:|
| 0.8 | 3.9402e-13 | 0.0281475 | 7.14367e+10 |
| 0.9 | 1.39008e-06 | 0.185302 | 133303 |
| 0.95 | 0.00140806 | 0.440127 | 312.576 |
| 0.99 | 0.276252 | 0.851458 | 3.08218 |
模拟构造4组实际128维向量,每组20000个,再测量其范数:全维均匀球、16维子空间均匀球、同样16稀疏但采用原128维球半径分布、以及全部固定在半径R的16稀疏点。前两者验证条件定理;后两者说明仅凭稀疏不能保证内部概率增加。
所有组外半径相同,但平均范数并未强行匹配。若把每个向量都归一化为相同范数,径向差异会被直接抹去。固定半径组的浮点误差约1e-16;理论上全部在球面,图中仅为数值表示。
这不证明好模型的参数更靠内部。用于模型时还需明确采样单元、中心、半径和缩放约定;参数可做保持功能的重参数化,原点距离不是模型质量不变量。
文件:run.py为生成程序;measured-radii.npz为全部实测范数;interior-probabilities.csv保留理论与经验概率;三种图格式及SHA清单便于长期保存。没有读取、训练或改动任何模型。
有限样本说明:每组20000个点不足以精确估计约1e-6的极小尾概率;极小概率和倍数以解析公式为准,不把零次命中当成严格零概率。
+41
View File
@@ -0,0 +1,41 @@
{
"passed": true,
"ambient_dimension": 128,
"sparse_dimensions": 16,
"sample_count_per_distribution": 20000,
"seed": 20261111,
"outer_radius": 1,
"controls": {
"uniform_d_ball": {
"active_dimensions": 128,
"max_norm": 0.9999994375833048,
"mean_squared_norm": 0.9846031601593415,
"radial_dimension": 128
},
"uniform_k_ball": {
"active_dimensions": 16,
"max_norm": 0.999996278718437,
"mean_squared_norm": 0.8894302831319619,
"radial_dimension": 16
},
"sparse_same_radial": {
"active_dimensions": 16,
"max_norm": 0.9999995857902936,
"mean_squared_norm": 0.9847321079586993,
"radial_dimension": 128
},
"sparse_sphere": {
"active_dimensions": 16,
"max_norm": 1.0000000000000002,
"mean_squared_norm": 1.0,
"radial_dimension": null
}
},
"elapsed_seconds": 3.858549994882196,
"limitations": [
"synthetic distributions, not trained-network parameters",
"same outer radius, not same mean squared norm",
"changing angular support alone leaves the chosen radial law unchanged",
"fixed-radius shell is a deliberately structured counterexample"
]
}
+9
View File
@@ -0,0 +1,9 @@
{
"REPORT.md": "aca991f55ab215f637e310430eef267b0d2a327bb11be5ebdefb8a759fe5a4e5",
"audit.json": "a9c294b86872676ad2cd721d6e4ab819f01ecb43194829246d2505d2fa5a4555",
"interior-probabilities.csv": "e1aaddec9b4079d212a43c05b2b348e449bb6a120314225558ed4a7624de7f28",
"measured-radii.npz": "6a44587524196f4281f43753c87146344a38b72e141d7c06135385cd680b613c",
"sparse_shell_controls.pdf": "d2f749b107b391b58a5309ad14383c41716dc864c0e24d2b517cc1f8f6aa6da2",
"sparse_shell_controls.png": "7d4a6810838a7d377e0e68f19a952baa6784e3fa5a112396f5cbd65e61992eb1",
"sparse_shell_controls.svg": "b34aa1f561b316c06d0c620f594c1e3a64bcaa1ce2cb175d69946e867822b43d"
}
@@ -0,0 +1,17 @@
distribution,radius_fraction,theory_probability,empirical_probability,sample_count
uniform_d_ball,0.8,3.940200619639476e-13,0.0,20000
uniform_k_ball,0.8,0.028147497671065624,0.02645,20000
sparse_same_radial,0.8,3.940200619639476e-13,0.0,20000
sparse_sphere,0.8,0.0,0.0,20000
uniform_d_ball,0.9,1.3900845237714517e-06,0.0,20000
uniform_k_ball,0.9,0.18530201888518416,0.1821,20000
sparse_same_radial,0.9,1.3900845237714517e-06,0.0,20000
sparse_sphere,0.9,0.0,0.0,20000
uniform_d_ball,0.95,0.001408061023535215,0.0012,20000
uniform_k_ball,0.95,0.44012666865176536,0.4402,20000
sparse_same_radial,0.95,0.001408061023535215,0.0011,20000
sparse_sphere,0.95,0.0,0.0,20000
uniform_d_ball,0.99,0.2762516676992083,0.27975,20000
uniform_k_ball,0.99,0.8514577710948755,0.8515,20000
sparse_same_radial,0.99,0.2762516676992083,0.27645,20000
sparse_sphere,0.99,0.0,0.0,20000
1 distribution radius_fraction theory_probability empirical_probability sample_count
2 uniform_d_ball 0.8 3.940200619639476e-13 0.0 20000
3 uniform_k_ball 0.8 0.028147497671065624 0.02645 20000
4 sparse_same_radial 0.8 3.940200619639476e-13 0.0 20000
5 sparse_sphere 0.8 0.0 0.0 20000
6 uniform_d_ball 0.9 1.3900845237714517e-06 0.0 20000
7 uniform_k_ball 0.9 0.18530201888518416 0.1821 20000
8 sparse_same_radial 0.9 1.3900845237714517e-06 0.0 20000
9 sparse_sphere 0.9 0.0 0.0 20000
10 uniform_d_ball 0.95 0.001408061023535215 0.0012 20000
11 uniform_k_ball 0.95 0.44012666865176536 0.4402 20000
12 sparse_same_radial 0.95 0.001408061023535215 0.0011 20000
13 sparse_sphere 0.95 0.0 0.0 20000
14 uniform_d_ball 0.99 0.2762516676992083 0.27975 20000
15 uniform_k_ball 0.99 0.8514577710948755 0.8515 20000
16 sparse_same_radial 0.99 0.2762516676992083 0.27645 20000
17 sparse_sphere 0.99 0.0 0.0 20000
Binary file not shown.
Binary file not shown.
Binary file not shown.

After

Width:  |  Height:  |  Size: 160 KiB

File diff suppressed because it is too large Load Diff

After

Width:  |  Height:  |  Size: 125 KiB