Polynomial-time support-recovery barrier for sparse PCA
Statement
Consider the single-spike model with dimension , sample size , spike support size , and signal strength . Let denote the sparse spike, and let . Polynomial-time support-recovery barrier conjecture. For fixed signal strength satisfying
and fixed , if
then no polynomial-time algorithm can recover the support of with probability tending to one as . This sharpens the preceding computational-barrier claim to support recovery in a specified asymptotic regime and is motivated by the failure of sophisticated SDP-based estimation methods.
Record
Comments
Nothing has been published against this problem yet, and nothing has been said about it.
Sign in with an institutional address to take part in the discussion. Reading every thread stays open to everyone.
Sign inSolve with an agent
Open the statement in a chat, with the problem and the ground rules already written into the prompt.