- Bob mentions his Asilomar 2011 Slides entitled Cyclic Greedy Algorithms for Recovering Compressively Sampled Sparse Signals and I am looking for the conclusion of his next talk, but I would be careful if I were him as he could adopt the wrong conclusions: our side of the Force will take down whoever stray :-)
- Zhilin talks about A phenomenon indicating a possible incorrect calling of T-MSBL
- Laurent has a call for papers: Advances in signal and image processing for physico-chemical analysis
PS: The slide is from Bob's presentation and yes, you're reading this right, SL0 beats all of them hands down!
Liked this entry ? subscribe to Nuit Blanche's feed, there's more where that came from. You can also subscribe to Nuit Blanche by Email, explore the Big Picture in Compressive Sensing or the Matrix Factorization Jungle and join the conversations on compressive sensing, advanced matrix factorization and calibration issues on Linkedin.
Dear Igor,
ReplyDeleteNote that I am not the one who delivered the "snake oil" talk. That was by Fred Daum of Raytheon. I can't find his slides, but his message was this: as far as he can see, the area in which compressed sensing can make any impact in radar is extremely limited.
Also note that Probabilistic OMP beats SL0 at lower problem indeterminaces.
ReplyDeleteOh ok, i see the snake oil talk
ReplyDeletehttp://ieeexplore.ieee.org/Xplore/login.jsp?url=http%3A%2F%2Fieeexplore.ieee.org%2Fiel5%2F4798978%2F4800289%2F04800326.pdf%3Farnumber%3D4800326&authDecision=-203
It is about MIMO radar.
Yes OMP does better than SL0 sometimes