关于「稀疏也能补全:低秩矩阵需要多少个观测条目」,《稀疏购买记录的偏好补全》给出的定量结论是什么?
结论:第一章扫描观测比例:40 乘 40、秩二的矩阵在观测数为自由度 2.05 倍时误差中位数降到 0.0021,并用精确二项尾概率说明所需观测与 n r ln n 之比从 0.677 缓降到 0.436,对数因子去不掉。
数据口径:书中顾客数、商品数、口味维度与购买概率均为示意参数;全部计算由书中程序生成;本书属于非个人化经营建议,推荐流程只用店铺自有数据,不外传个人数据,不做跨平台追踪。 第七章考辨《周易·系辞上》「方以类聚,物以群分」与斯皮尔曼 1904 年的一般因素,指出纯分群与混合成员下两种模型各有胜负。
对照数据表
下表数字由本章 Python 程序原样打印,可重新运行复现。 程序只用 Python 标准库与结论吻合的打印值: 0.0021, 2.05, 40
| n = 40, rank 2, dof = 156, n r ln n = 295 | ||||
| p | mean m | m/dof | median err | success |
| 0.06 | 93.0 | 0.60 | 24.5020 | 0/5 |
| 0.10 | 160.2 | 1.03 | 11.1119 | 0/5 |
| 0.15 | 247.4 | 1.59 | 8.2153 | 1/5 |
| 0.20 | 319.4 | 2.05 | 0.0021 | 3/5 |
| 0.25 | 402.8 | 2.58 | 0.0001 | 5/5 |
| 0.30 | 482.4 | 3.09 | 0.0000 | 5/5 |
| 0.40 | 642.4 | 4.12 | 0.0000 | 5/5 |
查看完整验算程序
# Chapter 1. p12: recovery error against the observed share.
# Model: a 40 x 40 matrix of rank 2 with Gaussian factors (an
# incoherent matrix, illustrative). Entries are observed independently
# with probability p; alternating least squares (rank 2, ridge 1e-5,
# 80 sweeps, spectral start as in p33) fills the rest. Error is the
# relative root-mean-square error on the unobserved cells; success
# means error below 0.01. Five fixed seeds per row.
import math
import random
def dot(a, b):
return math.fsum(x * y for x, y in zip(a, b))
def solve(A, b):
# Gaussian elimination with partial pivoting for a small system
n = len(b)
M = [list(A[i]) + [b[i]] for i in range(n)]
for k in range(n):
p = max(range(k, n), key=lambda i: abs(M[i][k]))
M[k], M[p] = M[p], M[k]
for i in range(k + 1, n):
f = M[i][k] / M[k][k]
M[i] = [M[i][j] - f * M[k][j] for j in range(n + 1)]
x = [0.0] * n
for i in range(n - 1, -1, -1):
s = math.fsum(M[i][j] * x[j] for j in range(i + 1, n))
x[i] = (M[i][n] - s) / M[i][i]
return x
def update(trip, F, r, lam, prior=None):
# weighted ridge step for one row: minimise
# sum w (y - f.x)^2 + lam |x - prior|^2 over x
pr = prior if prior is not None else [0.0] * r
A = [[math.fsum(w * F[j][a] * F[j][b] for j, _, w in trip)
+ (lam if a == b else 0.0) for b in range(r)]
for a in range(r)]
y = [math.fsum(w * F[j][a] * v for j, v, w in trip) + lam * pr[a]
for a in range(r)]
return solve(A, y)
def als(nu, ni, obs, r, lam, iters, seed, V=None, trace=None):
# alternating least squares on (u, i, value, weight) tuples
rng = random.Random(seed)
if V is None:
V = [[rng.gauss(0.0, 1.0) for _ in range(r)] for _ in range(ni)]
bu = [[] for _ in range(nu)]
bi = [[] for _ in range(ni)]
for u, i, x, w in obs:
bu[u].append((i, x, w))
bi[i].append((u, x, w))
U = None
for t in range(iters):
U = [update(bu[u], V, r, lam) for u in range(nu)]
V = [update(bi[i], U, r, lam) for i in range(ni)]
if trace is not None:
trace.append((t + 1, U, V))
return U, V
def factors(n, r, rng):
return [[rng.gauss(0.0, 1.0) for _ in range(r)] for _ in range(n)]
def product(A, B):
return [[dot(a, b) for b in B] for a in A]
def mask(nu, ni, p, rng):
return [(u, i) for u in range(nu) for i in range(ni)
if rng.random() < p]
def relerr(M, U, V, cells):
num = math.fsum((dot(U[u], V[i]) - M[u][i]) ** 2 for u, i in cells)
den = math.fsum(M[u][i] ** 2 for u, i in cells)
return math.sqrt(num / den)
def rmse(M, U, V, cells):
num = math.fsum((dot(U[u], V[i]) - M[u][i]) ** 2 for u, i in cells)
return math.sqrt(num / len(cells))
def orthonormal(cols):
# Gram-Schmidt on a list of column vectors
out = []
for c in cols:
v = list(c)
for q in out:
h = dot(q, v)
v = [a - h * b for a, b in zip(v, q)]
nv = math.sqrt(dot(v, v))
out.append([a / nv for a in v])
return out
def spectral(nu, ni, cells, r, rng, iters=30):
# top-r right singular subspace of the rescaled observed matrix:
# Y[u][i] = x / p for observed cells, 0 elsewhere
Y = [[0.0] * ni for _ in range(nu)]
for u, i, x, p in cells:
Y[u][i] = x / p
Yt = [list(c) for c in zip(*Y)]
Q = orthonormal([[rng.gauss(0, 1) for _ in range(ni)]
for _ in range(r)])
for _ in range(iters):
Q = orthonormal([[dot(row, [dot(y, q) for y in Y]) for row in Yt]
for q in Q])
return [[Q[k][i] for k in range(r)] for i in range(ni)]
n, r = 40, 2
dof = r * (2 * n - r)
print("n = 40, rank 2, dof = {}, n r ln n = {:.0f}".format(
dof, n * r * math.log(n)))
print(" p mean m m/dof median err success")
for p in (0.06, 0.10, 0.15, 0.20, 0.25, 0.30, 0.40):
errs, ms = [], []
for s in range(5):
rng = random.Random(20261113 + 101 * s)
M = product(factors(n, r, rng), factors(n, r, rng))
seen = mask(n, n, p, rng)
ss = set(seen)
rest = [(u, i) for u in range(n) for i in range(n)
if (u, i) not in ss]
obs = [(u, i, M[u][i], 1.0) for u, i in seen]
V0 = spectral(n, n, [(u, i, x, p) for u, i, x, _ in obs], r, rng)
U, V = als(n, n, obs, r, 1e-5, 80, 7 + s, V=V0)
errs.append(relerr(M, U, V, rest))
ms.append(len(seen))
errs.sort()
ok = len([e for e in errs if e < 0.01])
m = math.fsum(ms) / len(ms)
print(" {:.2f} {:6.1f} {:5.2f} {:.4f} {}/5".format(
p, m, m / dof, errs[2], ok))唯一数据源与引用
范雅福(Fan, Y.). (2026). 《低秩矩阵补全与交替最小二乘、稀疏购买记录推断未表态偏好母典》第 1 章「稀疏也能补全:低秩矩阵需要多少个观测条目」(版本 1.0.0). 5D Library. DOI 待发布
DOI 待发布 · 专著页正式发布后上线(本站暂无专著页) · 5DL-B-328 · v1.0.0 · CC-BY-NC-ND-4.0
BibTeX
@book{fan2026328,
author = {Fan, Yafu},
title = {Low-Rank Matrix Completion and Alternating Least Squares: Inferring Unstated Preferences from Sparse Purchase Records},
year = {2026},
publisher = {5D Library},
edition = {1.0.0},
note = {DOI pending}
}