PaperScope
LIVE · 2026-09-07 05:40 UTC

Dimension-Adaptive Batched Lipschitz Narrowing Without Knowing the Zooming Dimension

Yasong Feng

Latestcs.CLcs.LGcs.AIcs.CV
arXiv ID
2609.05214 v1
Category
Submitted
2026-09-04

Abstract

The Appropriately Combined Edge-length (ACE) sequence in A-BLiN depends on the zooming dimension $d_z$. This note removes that dependence. The next edge length is selected from the number of cubes that survive the preceding elimination. The resulting Count-Adaptive BLiN algorithm does not use $d_z$ or the zooming constant $C_z$, yet it attains $\widetilde{\mathcal O}_d(T^{(d_z+1)/(d_z+2)})$ regret with $\mathcal O_d(\log\log T)$ batches. Together with the adaptive-grid lower bound in Theorem 10 of the original paper, the optimal batch complexity remains $Θ_d(\log\log T)$ when $d_z$ is unknown.

arXiv abs page · PDF · same-day batch