ROBUST SUBSPACE TRACKING WITH CONTAMINATION MITIGATION VIA $\alpha$-DIVERGENCE
LE Trung Thanh (University of Orleans); Aref Miri Rekavandi (University of Melbourne, Melbourne, Australia); Abd-Krim Seghouane (University of Mebourne); KARIM ABED-MERAIM (PRISME laboratory, university of Orleans, France)
-
Members: FreeSPS
IEEE Members: $11.00
Non-members: $15.00
06 Jun 2023
We studied the problem of robust subspace tracking (RST) in contaminated environments. Leveraging the fast approximated power iteration and $\alpha$-divergence, a novel robust algorithm called $\alpha$FAPI was developed for tracking the underlying principal subspace of streaming data over time. $\alpha$FAPI is fast and it outperforms many RST methods while only having a low complexity linear to the data dimension. Some experiments were conducted to illustrate the performance of $\alpha$FAPI.
