变量选择很难
Variable Selection is Hard
摘要:
稀疏线性回归的变量选择是这样的问题:给定一个m × p矩阵B和一个目标向量y,找到一个稀疏向量x,使得Bx近似等于y。假设一个标准的复杂性假设,我们证明了没有多项式时间算法可以找到一个k '-稀疏x,||Bx-y||其中k ′ = k*2^{log^{1-delta} p},h(m,p)≤ p^(C_1)*m^(1-C_2),其中delta>0,C_1> 0,C_2>0是任意的。即使在存在未知k-稀疏向量x^* 满足Bx^*=y的承诺下,这也是正确的。我们证明了一个类似的结果的统计版本的问题,其中的数据被噪声破坏。据作者所知,这些是当算法同时具有k '> k和h(m,p)>0时适用的稀疏回归的第一个硬度结果。
英文摘要:
Variable selection for sparse linear regression is the problem of finding, given an m x p matrix B and a target vector y, a sparse vector x such that Bx approximately equals y. Assuming a standard complexity hypothesis, we show that no polynomial-time algorithm can find a k'-sparse x with ||Bx-y||^2<=h(m,p), where k'=k*2^{log^{1-delta} p} and h(m,p)<=p^(C_1)*m^(1-C_2), where delta>0, C_1>0,C_2>0 are arbitrary. This is true even under the promise that there is an unknown k-sparse vector x^* satisfying Bx^*=y. We prove a similar result for a statistical version of the problem in which the data are corrupted by noise. To the authors' knowledge, these are the first hardness results for sparse regression that apply when the algorithm simultaneously has k'>k and h(m,p)>0.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。