arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2111.14486cs.LGeess.SPstat.ML
收藏

Just Least Squares:低生成内维数的二进制压缩采样

Just Least Squares: Binary Compressive Sampling with Low Generative Intrinsic Dimension

Wuhan University(武汉大学)

Yuling Jiao, Dingwei Li, Min Liu, Xiangliang Lu, Yuanyuan Yang

摘要:

在本文中,我们考虑恢复$n$维信号从$m$二进制测量被噪声和符号翻转损坏的假设下,目标信号具有低生成本征维数,即,目标信号可以通过$L$发生器$G: \mathbb{R}^k\rightarrow\mathbb{R}^{n}, k\ll n$近似地产生。虽然二进制测量模型是高度非线性的,我们提出了一个最小二乘解码器,并证明,直到一个恒定的$c$,具有很高的概率,最小二乘解码器实现了尖锐的估计误差$\mathcal{O} (\sqrt{\frac{k\log (Ln)}{m}})$,只要$m\geq \mathcal{O}( k\log (Ln))$。大量的数值模拟和国家的最先进的方法的比较表明,最小二乘解码器是强大的噪声和符号翻转,我们的理论所示。通过构建具有适当选择的深度和宽度的ReLU网络,我们验证了(近似)深度生成先验,这是独立的兴趣。

英文摘要:

In this paper, we consider recovering $n$ dimensional signals from $m$ binary measurements corrupted by noises and sign flips under the assumption that the target signals have low generative intrinsic dimension, i.e., the target signals can be approximately generated via an $L$-Lipschitz generator $G: \mathbb{R}^k\rightarrow\mathbb{R}^{n}, k\ll n$. Although the binary measurements model is highly nonlinear, we propose a least square decoder and prove that, up to a constant $c$, with high probability, the least square decoder achieves a sharp estimation error $\mathcal{O} (\sqrt{\frac{k\log (Ln)}{m}})$ as long as $m\geq \mathcal{O}( k\log (Ln))$. Extensive numerical simulations and comparisons with state-of-the-art methods demonstrated the least square decoder is robust to noise and sign flips, as indicated by our theory. By constructing a ReLU network with properly chosen depth and width, we verify the (approximately) deep generative prior, which is of independent interest.

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。

↑