Kardashev

Hacker News New2026-10-07 16:450 views

Points: 1

# Comments: 0

$Sharp Non-Asymptotic Analysis of the Penalized Challenger in $\beta$-EB-TCI for Bernoulli Bandits$

arXiv:2610.01951v2 Announce Type: replace-cross Abstract: Top-two algorithms are simple and effective for fixed-confiden

arXiv:2609.13547v2 Announce Type: replace-cross Abstract: We study switching regret in adversarial multi-armed bandits,

$Spectral Condition for $\mu$P under Width-Depth Scaling$

arXiv:2603.00541v3 Announce Type: replace-cross Abstract: Generative foundation models are increasingly scaled in both w

arXiv:2602.03514v3 Announce Type: replace-cross Abstract: Modern learning systems often interpolate training data while

arXiv:2510.22069v2 Announce Type: replace-cross Abstract: Problem definition: Hospitals use separate pathways to identif

arXiv:2608.25182v2 Announce Type: replace Abstract: In this paper, we study alternating regret in online convex optimiza

Related posts