AI Paper Atlas

Research map / Bandits and online learning / Contextual bandits and Thompson sampling

Sequential Experimental Design for Transductive Linear Bandits

Tanner Fiez, Lalit Jain, Kevin G. Jamieson, Lillian Ratliff

NeurIPS 2019 · Bandits and online learning › Contextual bandits and Thompson sampling · approach: Linear and generalized linear bandits · 9 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Use sequential gap-based allocation and eliminate arms that are provably suboptimalTransductive linear bandits · Transductive linear banditssample complexityImproved
Adapt sampling to the active arms rather than use a static XY allocationLinear bandits: benchmark example · Linear bandits: benchmark examplesample complexityImproved
Allocate measurements using differences between active vectors rather than a G-optimal design on the vectors themselvesRAGE · Uniform Distribution on a Spheresample complexityImproved
Use adaptive RAGE instead of static XY allocationTransductive example · Transductive examplesample complexityImproved
Sample each arm onceLinGapE · Many arms with moderate gapssample complexityHurt
Compute allocations on the measurement vectors rather than on differences between vectorsALBA · Linear bandits: benchmark examplesample complexityHurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy