A short version of this work is in ICML 2019, this longer version is published in IEEE Trans. Info. Th on March 2020. Fixing minor but important errors in Lemmas 3.10, 3.11, 3.12 statements and in proof of the Term1 bound. No change to Theorem statement
我们研究了低秩相位恢复(LRPR)问题,定义如下:恢复一个$n \times q$矩阵$X^*$的秩$r$从不同的和独立的一组$m$无相位(仅幅度)的线性投影的每一列。准确地说,当测量矩阵$A_k$相互独立时,我们需要从$y_k := |A_k{}' x^*_k|, k=1,2,\dots, q$恢复$X^*$。这里,$y_k$是$m$长度向量,$A_k$是$n \times m$矩阵,$'$表示矩阵转置。问题是我们什么时候可以用$m \ll n$解决LRPR?可靠的解决方案可以实现快速且低成本的无相位动态成像,例如,活体生物标本的傅立叶重叠关联成像。在这项工作中,我们开发了第一个可证明正确的方法来解决这个LRPR问题。我们提出的算法,交替最小化低秩相位恢复(AltMinLowRaP),是一个基于AltMin的解决方案,因此也是可证明的快速(几何收敛)。我们的保证表明,AltMinLowRaP以高概率将LRPR求解为$ε$精度,只要$m q \ge C n r^4 \log(1/ε)$,矩阵$A_k$包含i.i.d.标准高斯项,并且$X^*$的右奇异向量满足来自矩阵完备化文献的不相干假设。这里$C$是一个数值常数,它只取决于$X^*$的条件数和它的不相干参数。其时间复杂度仅为$ C mq nr \log^2(1/ε)$。由于即使是上述问题的线性(有相位)版本也没有完全解决,因此上述结果也是线性情况的第一个完整解决方案和保证。最后,我们还开发了一个简单的扩展我们的结果的动态LRPR设置。
英文摘要:
We study the Low Rank Phase Retrieval (LRPR) problem defined as follows: recover an $n \times q$ matrix $X^*$ of rank $r$ from a different and independent set of $m$ phaseless (magnitude-only) linear projections of each of its columns. To be precise, we need to recover $X^*$ from $y_k := |A_k{}' x^*_k|, k=1,2,\dots, q$ when the measurement matrices $A_k$ are mutually independent. Here $y_k$ is an $m$ length vector, $A_k$ is an $n \times m$ matrix, and $'$ denotes matrix transpose. The question is when can we solve LRPR with $m \ll n$? A reliable solution can enable fast and low-cost phaseless dynamic imaging, e.g., Fourier ptychographic imaging of live biological specimens. In this work, we develop the first provably correct approach for solving this LRPR problem. Our proposed algorithm, Alternating Minimization for Low-Rank Phase Retrieval (AltMinLowRaP), is an AltMin based solution and hence is also provably fast (converges geometrically). Our guarantee shows that AltMinLowRaP solves LRPR to $ε$ accuracy, with high probability, as long as $m q \ge C n r^4 \log(1/ε)$, the matrices $A_k$ contain i.i.d. standard Gaussian entries, and the right singular vectors of $X^*$ satisfy the incoherence assumption from matrix completion literature. Here $C$ is a numerical constant that only depends on the condition number of $X^*$ and on its incoherence parameter. Its time complexity is only $ C mq nr \log^2(1/ε)$. Since even the linear (with phase) version of the above problem is not fully solved, the above result is also the first complete solution and guarantee for the linear case. Finally, we also develop a simple extension of our results for the dynamic LRPR setting.
Provable Inductive Robust PCA via Iterative Hard Thresholding
Microsoft Corporation(微软公司);Conduent Labs India(Conduent印度实验室);University of Illinois Chicago(伊利诺伊大学芝加哥分校);University of California Irvine(加利福尼亚大学尔湾分校);Xerox Research Centre India(施乐印度研究中心)
Learning on Transformers is Provable Low-Rank and Sparse: A One-layer Analysis
Rensselaer Polytechnic Institute(伦斯勒理工学院);New Jersey Institute of Technology(新泽西理工学院);Michigan State University(密歇根州立大学);IBM Thomas J. Watson Research Center(IBM托马斯·J·沃森研究中心)
Chandra Family Department of Electrical and Computer Engineering, The University of Texas at Austin, Austin, TX, USA(Chandra Family 电子与计算机工程系,德克萨斯大学奥斯汀分校);Snap, Inc.(Snap公司);Google Research(Google研究)
Long Context Modeling with Ranked Memory-Augmented Retrieval
University of New South Wales(新南威尔士大学);Hong Kong University of Science and Technology (Guangzhou)(香港科技大学(广州));The Hong Kong University of Science and Technology(香港科技大学);University of Southampton(南安普顿大学);Mohamed Bin Zayed University of Artificial Intelligence(穆罕默德·本·扎耶德人工智能大学)