AI Paper Atlas

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

Multi-channel Autobidding with Budget and ROI Constraints

ICML 2023 · Bandits and online learning › Online convex optimization and games · approach: Learning for pricing and auctions · 9 citations (OpenAlex)

Read the paperCheck your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's title only (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
optimize only per-channel target ROIs (no budget lever)multi-channel advertiser problem · theoretical example (2 channels, 3 auctions)CH-OPT(I_R)/GL-OPT ratio: ratio approaches 0 as X growsHurt
optimize only per-channel budgets (budget-only lever)multi-channel advertiser problem · theoreticaltotal conversion vs GL-OPT: equals GL-OPTHelped
augment per-channel budget learning with UCB (SGD-UCB) under bandit feedbackper-channel budget optimization · synthetic, T=200, optimal autobiddingconversion as % of GL-OPT: more than 91% of global optimalHelped
increase number of periods T from 100 to 1000 (ablation)SGD-UCB · synthetic, optimal autobiddingconversion as % of GL-OPT and varianceHelped
lower channel autobidding optimality (corruption factors alpha from 1 down to 0.2) (ablation)SGD-UCB · synthetic, T=200, normalized conversionconversion as % of optimal normalized conversionMixed

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