AI Paper Atlas

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

Non-stationary Online Learning with Memory and Non-stochastic Control

Peng Zhao, Yu-Hu Yan, Yu-Xiang Wang, Zhi-Hua Zhou

JMLR 2023 · Bandits and online learning › Online convex optimization and games · approach: Parameter-free non-stationary online learning · 14 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
add meta-base switching-cost-regularized loss (Scream) versus OGD at small regularizer alpha=0.1Scream · OCO with switching cost (T=50000, d=10)overall lossNo clear effect
use Scream versus Ader and OGD at medium regularizer alpha=1Scream · OCO with switching cost (T=50000, d=10)overall lossImproved
use Scream versus OGD at large regularizer alpha=2Scream · OCO with switching cost (T=50000, d=10)overall lossNo clear effect
ignore switching cost (Ader) at large regularizer alpha=2Ader · OCO with switching cost (T=50000, d=10)overall lossHurt
use Scream.Control versus OGD.Control and Ader.ControlScream.Control · Time-varying LDS, gradual changecumulative costImproved
use Scream.Control versus OGD.Control and Ader.ControlScream.Control · Time-varying LDS, abrupt changecumulative costImproved
use Scream.Control versus OGD.Control and Ader.ControlScream.Control · Inverted pendulumcumulative costImproved

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