AI Paper Atlas

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

CLASP: Online learning algorithms for Convex Losses And Squared Penalties

Ricardo N. Ferreira, Joao Xavier, Claudia Soares

ICML 2026 · Bandits and online learning › Online convex optimization and games · approach: Constrained and unconstrained OCO algorithms

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 CLASP (gradient step plus projection onto current constraint set) instead of AdaGrad-based methodonline constrained convex optimization · Online linear regression with adversarial constraints (synthetic)CCV_T,1 and CCV_T,2Improved
CLASP versus RECOOonline linear regression · Online linear regression with adversarial constraints (synthetic)CCV_T,1 and CCV_T,2No clear effect
use Switch instead of CLASPonline linear regression · Online linear regression with adversarial constraints (synthetic)constraint violation and per-iteration costMixed
CLASP versus AdaGrad and RECOO on constraint violationonline SVM on wine quality data · Online SVM, wine quality (feasibility not satisfied)CCV_T,1 and CCV_T,2Improved
longer horizon, CLASP versus RECOOonline linear regression with additional rounds · Online linear regression (more rounds, Switch removed)CCV_T,2 variabilityImproved

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