# And finally, a little Probabilistic OMP

Following on the heels of the previous post, and the post previous to that, post previous to that, and the post previous to that, I am now comparing recovery performance of Probabilistic OMP (PrOMP), and straight-up OMP. In my implementation of PrOMP, I limit the number of independent trials to 10. Furthermore, I make $$\epsilon = 0.001$$, and I set the number of high probability atoms to 2. The end condition tolerance is the same as for OMP ($$||\vr||/||\vx|| < 10^{-5}$$). Click on the image below to see the results.

No matter the category of sparse vector distribution, PrOMP is like the Walt Disney of greedy methods: it wins the most Oscars, and apparently has fun doing it too. These results confirm my earlier ones here, and here.

Overall, a highly productive day considering the time change!

If you wish to reproduce these results at home, then use this MATLAB code. (CVX needed.) Let me know of any bugs!