AI Paper Atlas

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

Random Permutation Online Isotonic Regression

Wojciech Kotlowski, Wouter M. Koolen, Alan Malek

NeurIPS 2017 · Bandits and online learning › Online convex optimization and games · approach: Online learning with feedback graphs · 3 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 the online-to-batch conversion of the optimal fixed-design algorithm (random permutation learner from Eq. 3)online isotonic regression in random permutation model · theoretical regret boundexcess leave-one-out loss / regretImproved
Forward algorithms (any label estimate) analyzed in random permutation modelforward algorithms · theoretical regret boundexcess leave-one-out lossNo clear effect
Forward algorithms analyzed in well-specified (i.i.d. noise around isotonic means) settingforward algorithms · well-specified caseexcess leave-one-out lossImproved
Use IR-Int (interpolation) forward algorithm on adversarial alternating-segment label sequenceIR-Int forward algorithm · hard label sequence (segments with proportion k/n of ones)excess leave-one-out lossHurt
Heavy-γ with weight c=Θ(t^{1/3}) on the current instance (conjectured)forward algorithm with heavy weighting · theoretical conjectureexcess leave-one-out lossNo clear effect
Log-IVAP forward algorithm under entropic loss instead of squared losslog-IVAP · entropic lossexcess leave-one-out lossNo clear effect
Plugging in the IR-Int label estimate into any weighted forward scheme (Heavy-type) with any weightHeavy-style forward algorithms · theoreticalexcess leave-one-out lossHurt

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