Finite Sample Analysis of Approximate Message Passing Algorithms
This provides theoretical support for the empirical performance of AMP in high-dimensional statistical estimation, addressing a gap in non-asymptotic analysis for researchers in signal processing and machine learning.
The paper tackles the problem of analyzing Approximate Message Passing (AMP) algorithms in finite sample regimes, deriving a concentration inequality that shows the probability of deviation from state evolution predictions decays exponentially with problem dimension, and indicating that the number of iterations can grow at most as O(log n / log log n) for high-probability accuracy.
Approximate message passing (AMP) refers to a class of efficient algorithms for statistical estimation in high-dimensional problems such as compressed sensing and low-rank matrix estimation. This paper analyzes the performance of AMP in the regime where the problem dimension is large but finite. For concreteness, we consider the setting of high-dimensional regression, where the goal is to estimate a high-dimensional vector $β_0$ from a noisy measurement $y=A β_0 + w$. AMP is a low-complexity, scalable algorithm for this problem. Under suitable assumptions on the measurement matrix $A$, AMP has the attractive feature that its performance can be accurately characterized in the large system limit by a simple scalar iteration called state evolution. Previous proofs of the validity of state evolution have all been asymptotic convergence results. In this paper, we derive a concentration inequality for AMP with i.i.d. Gaussian measurement matrices with finite size $n \times N$. The result shows that the probability of deviation from the state evolution prediction falls exponentially in $n$. This provides theoretical support for empirical findings that have demonstrated excellent agreement of AMP performance with state evolution predictions for moderately large dimensions. The concentration inequality also indicates that the number of AMP iterations $t$ can grow no faster than order $\frac{\log n}{\log \log n}$ for the performance to be close to the state evolution predictions with high probability. The analysis can be extended to obtain similar non-asymptotic results for AMP in other settings such as low-rank matrix estimation.