Theoretical analysis of comparable test performance among block preconditioners
Establish a rigorous theoretical analysis explaining why the standard Block Jacobi preconditioner, the hybrid block preconditioner, and the BLOKS sketched block Jacobi preconditioner exhibit almost indistinguishable test-time performance, and determine whether regularization effects caused by block approximation account for this phenomenon.
References
We believe this phenomenon might be partly caused by additional regularization introduced by the approximation of the blocks, and we leave a rigorous theoretical analysis for future work.
— BLOKS: Scaling Kernel Solvers with Sketched Block Preconditioning
(2610.13382 - Vitale et al., 9 Oct 2026) in Appendix, Section “Block preconditioning strategies and comparisons” (Section \ref{apx:block_prec})