AI & ML
Beyond the error horizon: averaged quantile Kaczmarz methods for corrupted and noisy linear systems
arXiv cs.NA0 views
arXiv:2611.21926v1 Announce Type: new Abstract: Linear systems and least-squares problems can contain measurement errors of different scales: a few measurements may be highly unreliable, while small noise affects every measurement. Residual-based iterative filtering can remove the influence of sparse corruption, but its accuracy is limited by a noise-dependent error horizon. We study how averaging and relaxation reduce this horizon in averaged quantile randomized Kaczmarz (AQRK), which filters equations by residual quantiles and averages a batch of single-row updates. Filtering, however, introduces an update bias that averaging alone cannot remove. We show that re-querying the accepted equations can remove this bias, and when the corruption is sparse enough relative to the conditioning of the matrix and large enough relative to the noise, we prove that AQRK with re-queried residuals reduces the horizon as averaging does without the corruption: its error decays to a horizon proportional to $\sqrt{\alpha/s}$, where $\alpha$ is the stepsize and $s$ the update batch size. Further, decreasing stepsizes or increasing batches gives convergence to the solution of the clean system. Numerical experiments support the theory and examine settings beyond it, including noise that cannot be re-queried and the corrupted low-rank tensor fitting problem. In the latter, AQRK inner solves succeed where standard alternating least-squares solvers and single-row robust updates fail.
Source:https://arxiv.org/abs/2611.21926PreviousForests of Omnitrees: Analysis and Applications to Anisotropic Space--Time Finite ElementsNextConvergence of discrete exterior calculus for the Hodge-Dirac and Hodge-Laplace problems on surfaces
Related posts

Google Home speakers get a major Gemini upgrade ‘soon,’ but only for paid subscribers
09to5Google

NVIDIA's CEO Shake-Up Exposes a Costly Prediction Market Deadline
0HackerNoon
Lumi-4B AI Model: Everything You Need to Know
0HackerNoon
The End of the Mouse: How AI Could Change the Way We Use Computers
0HackerNoon
How to Structure AI Adoption Teams and Measure Software Delivery Improvements
0HackerNoon
A Seven-Slide Framework for Funding AI Transformation Without New Headcount
0HackerNoon