S. C. Birgmeier, N. Görtz:

"Optimizing Approximate Message Passing for Variable Measurement Noise";

Poster: 26th European Signal Processing Conference (EUSIPCO) 2018, Rom; 09-03-2018 - 09-07-2018; in: "Proceedings EUSIPCO 2018", (2018), 489 - 493.

The standard Approximate Message Passing (AMP) algorithm optionally considers i.i.d. measurement noise. The governing parameter is the noise variance. When the noise is independent, but not identically distributed, applying AMP with the noise variance parameter set to the average of the actual noise variance results in significantly degraded performance. We propose a modified AMP algorithm called AMP-VN which

improves performance for known noise variances.

The standard Approximate Message Passing (AMP) algorithm optionally considers i.i.d. measurement noise. The governing parameter is the noise variance. When the noise is independent, but not identically distributed, applying AMP with the noise variance parameter set to the average of the actual noise variance results in significantly degraded performance. We propose a modified AMP algorithm called AMP-VN which

improves performance for known noise variances.

Approximate Message Passing, Compressed Sensing

Created from the Publication Database of the Vienna University of Technology.