{"ID":2863934,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2509.25429","arxiv_id":"2509.25429","title":"Feedback Control for Small Budget Pacing","abstract":"Budget pacing is critical in online advertising to align spend with campaign goals under dynamic auctions. Existing pacing methods often rely on ad-hoc parameter tuning, which can be unstable and inefficient. We propose a principled controller that combines bucketized hysteresis with proportional feedback to provide stable and adaptive spend control. Our method provides a framework and analysis for parameter selection that enables accurate tracking of desired spend rates across campaigns. Experiments in real-world auctions demonstrate significant improvements in pacing accuracy and delivery consistency, reducing pacing error by 13% and $λ$-volatility by 54% compared to baseline method. By bridging control theory with advertising systems, our approach offers a scalable and reliable solution for budget pacing, with particular benefits for small-budget campaigns.","short_abstract":"Budget pacing is critical in online advertising to align spend with campaign goals under dynamic auctions. Existing pacing methods often rely on ad-hoc parameter tuning, which can be unstable and inefficient. We propose a principled controller that combines bucketized hysteresis with proportional feedback to provide st...","url_abs":"https://arxiv.org/abs/2509.25429","url_pdf":"https://arxiv.org/pdf/2509.25429v2","authors":"[\"Sreeja Apparaju\",\"Yichuan Niu\",\"Xixi Qi\"]","published":"2025-09-29T19:38:34Z","proceeding":"cs.LG","tasks":"[\"cs.LG\",\"cs.GT\"]","methods":"[]","has_code":false}