AI Paper Atlas

Research map / Bandits and online learning / Online convex optimization and games

Fast Rates for Bandit Optimization with Upper-Confidence Frank-Wolfe

Quentin Berthet, Vianney Perchet

NeurIPS 2017 · Bandits and online learning › Online convex optimization and games · approach: Dynamic and adaptive regret · 0 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 lower-confidence gradient estimates to choose the Frank-Wolfe vertexBandit optimization with convex loss · C-smooth convex functions on Δ_Kexpected approximation error: 4 \sqrt{\frac{3K \log(T)}{T}}Improved
Assume the loss is minimized at a vertex and gradient component gaps are positiveUCB Frank-Wolfe · Convex functions minimized at a simplex vertexexpected approximation error: \frac{48 \log(T)}{T} \sum_{i \neq \star}\frac{1}{\Delta^{(i)}(L)}Improved
Assume strong convexity and an interior minimum at distance at least η from the boundaryUCB Frank-Wolfe · C-smooth strongly convex functions on Δ_Kexpected approximation error: c_1 \frac{\log^2(T)}{T} + c_2\frac{\log(T)}{T} + c_3 \frac{1}{T}Improved
Use only bandit feedback for linear losses rather than full gradient informationAny algorithm · Linear forms on Δ_Kminimax expected approximation error: c \sqrt{K/T}Hurt
Use mixed feedback where an action reveals information about another gradient coefficientAny algorithm · 1-strongly convex functions on Δ_3minimax expected approximation error: c/T^{2/3}Hurt

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