Construct · 1 fields · 1 citations

Lai-Robbins lower bound: a standalone construct

One name. One construct. A landmark on the map.

● anchor · a standalone construct Nearest construct by meaning·not indexed

A single standalone construct; nearby constructs are located against it in the Collider. Tap a field for its definition, unit, and measures.

Learning theory

the bound that any good multi-armed bandit strategy must incur regret growing at least logarithmically, with a constant set by distances between arm distributions.

In learning theory, Lai-Robbins lower bound refers to the bound that any good multi-armed bandit strategy must incur regret growing at least logarithmically, with a constant set by distances between arm distributions. This meaning comes from Lai (1985) in Advances in Applied Mathematics.[1]

Unit
Recovery means
Measured by

Run it through the Collider, or take the citations with you.

See how Lai-Robbins lower bound sits against neighbouring constructs in the Collider, or export every reference on this page in one click.

Open in Collider Export BibTeX Report this entry

Nearby constructs

bandit4 fields · 6 citationsjingle · one word, four constructs constant2 fields · 2 citationsjingle · one word, two constructs good2 fields · 5 citationsjingle · one word, two constructs

References

Lai, T. L., & Robbins, H. (1985). Asymptotically efficient adaptive allocation rules. Advances in Applied Mathematics, 6(1), 4-22. https://doi.org/10.1016/0196-8858(85)90002-8

Cited on this page?

Confirm your construct, or correct us.

If your work is cited behind one of these entries, you know better than we do whether we captured the meaning right. Confirm it, suggest an edit, or dispute it, and your name goes on the entry as an author who has checked it, linked to your ORCID.

Claim your construct