Learning Multiband Signals and Fourier-sparse Signals

Abstract

We consider efficient algorithms to learn multiband signals and Fourier-sparse signals. A mutliband signal has a Fourier transform supported by a bounded number of intervals, say $I_1 \cup I_2 \cdots \cup I_n$. There is a long line of research on multiband signals. In particular, Avron et al. showed an efficient reconstructing algorithm whose sample complexity is almost optimal. However, all previous algorithms for multiband signals consider the reconstructing problem in which the locations of $I_1,\ldots,I_n$ are given as a priori knowledge. On the other hand, although the problem of learning Fourier-sparse signals with $k$ arbitrary frequencies dates at least to Prony in 1795, designing efficient and robust learning algorithms is still an open problem. The state-of-the-art is an efficient algorithm of $\tilde{O}(k^3)$ samples and $\tilde{O}(k^{3 ω})$ time from the very recent work by Cai et al., while the statistical upper bound is $\tilde{O}(k^2)$ samples. Let $[-1,1]$ be the time window in which the noise is $\ell_2$ bounded. 1. We show an efficient algorithm to recover the locations of the bands $I_1,\ldots,I_n$ in $\hat{x}$ within $\tilde{O}(n+\sum_i |I_i|)$ samples and $\tilde{O}(n+\sum_i |I_i|)$ time. Furthermore, combining this with the reconstructing algorithm by Avron et al. provides an efficient interpolation algorithm within $\tilde{O}(n+\sum_i |I_i|)$ samples. 2. We show that every $k$-Fourier-sparse signal $x$ admits a multiband approximation $z$ whose Fourier transform is of support size $|\mathrm{supp}(\hat{z})|=\tilde{O}(k^2)$. Furthermore, we show an interpolation algorithm for $k$-Fourier-sparse signals with $\tilde{O}(k^2)$ samples and $\tilde{O}(k^5)$ time.