b-bit Marginal Regression

We consider the problem of sparse signal recovery from $m$ linear measurements quantized to $b$ bits. We study the question of choosing $b$ in the setting of a given budget of bits $B m \cdot b$ and derive a single easy-to-compute expression characterizing the trade-off between $m$ and $b$. The choice $b 1$ turns out to be optimal for estimating the unit vector corresponding to the signal for any level of additive Gaussian noise before quantization as well as for adversarial noise. For $b \geq 2$, we show that Lloyd-Max quantization constitutes an optimal quantization scheme and that the norm of the signal canbe estimated consistently by maximum likelihood. Papers published at the Neural Information Processing Systems Conference.