ORID d9JlreUNVY · tags icml2026-repro paper-d9JlreUNVY
| # | Status | Page | Artifact | Claim excerpt |
|---|---|---|---|---|
| 1 | VERIFIED 2/2 | 01-top-dogd-regret-convex-loss-functions | artifact | Top-DOGD achieves O(ω^{-1/2}ρ^{-1}n√T) regret for convex loss functions under co… |
| 2 | VERIFIED 2/2 | 02-top-dogd-regret-strongly-convex-loss | artifact | Top-DOGD achieves O(ω^{-1}ρ^{-2}n ln T) regret for strongly convex loss function… |
| 3 | VERIFIED 2/2 | 03-reduces-dependence-compression-quality-previousl | artifact | The paper reduces dependence on compression quality ω from the previously known … |
| 4 | VERIFIED 2/2 | 04-first-lower-bounds-decentralized-online | artifact | First lower bounds for decentralized online convex optimization with compressed … |
| 5 | VERIFIED 2/2 | 05-algorithm-combines-two-level-blocking-update | artifact | The algorithm combines a two-level blocking update framework with an online comp… |
| 6 | VERIFIED 2/2 | 06-bandit-feedback-extensions-are-provided-one-poin | artifact | Bandit-feedback extensions are provided: one-point feedback achieves O(ω^{-1/4}ρ… |