AI Paper Atlas

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

Stability-penalty-adaptive follow-the-regularized-leader: Sparsity, game-dependency, and best-of-both-worlds

Taira Tsuchiya, Shinji Ito, Junya Honda

NeurIPS 2023 · Bandits and online learning › Online convex optimization and games · approach: Online decision-making with feedback structure

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
Replace sparsity-aware tuned bound with s-agnostic SPA learning rateFTRL with SPA learning rate · MAB losses in [0,1], adversarialregret boundImproved
Use SPA learning rate for losses in [-1,1] instead of prior bound 10 sqrt(L2 log k) + 20 k log TFTRL with SPA learning rate · MAB losses in [-1,1], adversarialregret bound constants: 10 -> 4, 20 k log T -> 2 k log TImproved
Add best-of-both-worlds guarantee with sparsity-dependent boundSPA FTRL · MAB, stochastic regimeregret boundImproved
Make partial monitoring bound game-dependent and BOBW simultaneouslySPA FTRL · Non-degenerate local PM gamesregret boundImproved

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