# Multi-channel Autobidding with Budget and ROI Constraints arXiv: https://arxiv.org/abs/2302.01523 ยท HTML: https://mlsanity.com/paper/2302.01523/ ## Key facts - Cited by 14 papers in the map (data through 14 Oct 2026). - Builds on 26 of its 52 references that are in the map. - First posted on arXiv 3 Feb 2023. ## Builds on (most cited first, 26 of 26) - [Introduction to Multi-Armed Bandits](https://mlsanity.com/paper/1904.07272/) (2019) - [Taming the Monster: A Fast and Simple Algorithm for Contextual Bandits](https://mlsanity.com/paper/1402.0555/) (2014) - [Stochastic bandits robust to adversarial corruptions](https://mlsanity.com/paper/1803.09353/) (2018) - [Better Algorithms for Stochastic Bandits with Adversarial Corruptions](https://mlsanity.com/paper/1902.08647/) (2019) - [Learning to Optimize under Non-Stationarity](https://mlsanity.com/paper/1810.03024/) (2018) - [Efficient Contextual Bandits in Non-stationary Worlds](https://mlsanity.com/paper/1708.01799/) (2017) - [The Best of Many Worlds: Dual Mirror Descent for Online Allocation Problems](https://mlsanity.com/paper/2011.10124/) (2020) - [Selling to a No-Regret Buyer](https://mlsanity.com/paper/1711.09176/) (2017) - [A Unifying Framework for Online Optimization with Long-Term Constraints](https://mlsanity.com/paper/2209.07454/) (2022) - [Dynamic Incentive-aware Learning: Robust Pricing in Contextual Auctions](https://mlsanity.com/paper/2002.11137/) (2020) - [Contextual Bandits with Cross-learning](https://mlsanity.com/paper/1809.09582/) (2018) - [An Efficient Algorithm For Generalized Linear Bandit: Online Stochastic Gradient Descent and Thompson Sampling](https://mlsanity.com/paper/2006.04012/) (2020) - [Generalized Linear Bandits with Local Differential Privacy](https://mlsanity.com/paper/2106.03365/) (2021) - [Robust Auction Design in the Auto-bidding World](https://mlsanity.com/paper/2111.02468/) (2021) - [Autobidders with Budget and ROI Constraints: Efficiency, Regret, and Pacing Dynamics](https://mlsanity.com/paper/2301.13306/) (2023) - [Towards Efficient Auctions in an Auto-bidding World](https://mlsanity.com/paper/2103.13356/) (2021) - [Budget Pacing in Repeated Auctions: Regret and Efficiency without Convergence](https://mlsanity.com/paper/2205.08674/) (2022) - [Safe Convex Learning under Uncertain Constraints](https://mlsanity.com/paper/1903.04626/) (2019) - [Online Bidding Algorithms for Return-on-Spend Constrained Advertisers](https://mlsanity.com/paper/2208.13713/) (2022) - [Incentive-aware Contextual Pricing with Non-parametric Market Noise](https://mlsanity.com/paper/1911.03508/) (2019) - [Learning Product Rankings Robust to Fake Users](https://mlsanity.com/paper/2009.05138/) (2020) - [Auction Design in an Auto-bidding Setting: Randomization Improves Efficiency Beyond VCG](https://mlsanity.com/paper/2204.10956/) (2022) - [Efficiency of the First-Price Auction in the Autobidding World](https://mlsanity.com/paper/2208.10650/) (2022) - [Stochastic Zeroth-order Functional Constrained Optimization: Oracle Complexity and Applications](https://mlsanity.com/paper/2210.04273/) (2022) - [Constrained stochastic blackbox optimization using a progressive barrier and probabilistic estimates](https://mlsanity.com/paper/2011.04225/) (2020) - [Incentive Compatibility in the Auto-bidding World](https://mlsanity.com/paper/2301.13414/) (2023) ## Built on by (most cited first, 14 of 14) - [An Adaptable Budget Planner for Enhancing Budget-Constrained Auto-Bidding in Online Advertising](https://mlsanity.com/paper/2502.05187/) (2025) - [Multi-Platform Budget Management in Ad Markets with Non-IC Auctions](https://mlsanity.com/paper/2306.07352/) (2023) - [Interpolating Item and User Fairness in Multi-Sided Recommendations](https://mlsanity.com/paper/2306.10050/) (2023) - [Learning in Repeated Multi-Unit Pay-As-Bid Auctions](https://mlsanity.com/paper/2307.15193/) (2023) - [Online Ad Procurement in Non-stationary Autobidding Worlds](https://mlsanity.com/paper/2307.05698/) (2023) - [Enhancing Generative Auto-bidding with Offline Reward Evaluation and Policy Search](https://mlsanity.com/paper/2509.15927/) (2025) - [PRO-Bid: Pareto-Prioritized Regret Optimization for Constraint-Aware Generative Auto-Bidding](https://mlsanity.com/paper/2602.08261/) (2026) - [Model Monotonicity in Autobidding Auctions: When Do Better Predictions Lead to Better Outcomes?](https://mlsanity.com/paper/2605.31036/) (2026) - [Multi-channel Uplift Policy Learning](https://mlsanity.com/paper/2607.28182/) (2026) - [Advancing Ad Auction Realism: Practical Insights & Modeling Implications](https://mlsanity.com/paper/2307.11732/) (2023) - [Online Budget Allocation with Censored Semi-Bandit Feedback](https://mlsanity.com/paper/2508.05844/) (2025) - [HOB: A Holistically Optimized Bidding Strategy under Heterogeneous Bidding Environments](https://mlsanity.com/paper/2510.15238/) (2025) - [AHBid: An Adaptable Hierarchical Bidding Framework for Cross-Channel Advertising](https://mlsanity.com/paper/2602.22650/) (2026) - [Beyond Single-Episode Optimization: Sliding-Window Aware Generative Auto-Bidding for Long-Term Advertising Effectiveness](https://mlsanity.com/paper/2607.25233/) (2026) ## Abstract (arXiv) In digital online advertising, advertisers procure ad impressions simultaneously on multiple platforms, or so-called channels, such as Google Ads, Meta Ads Manager, etc., each of which consists of numerous ad auctions. We study how an advertiser maximizes total conversion (e.g. ad clicks) while satisfying aggregate return-on-investment (ROI) and budget constraints across all channels. In practice, an advertiser does not have control over, and thus cannot globally optimize, which individual ad auctions she participates in for each channel, and instead authorizes a channel to procure impressions on her behalf: the advertiser can only utilize two levers on each channel, namely setting a per-channel budget and per-channel target ROI. In this work, we first analyze the effectiveness of each of these levers for solving the advertiser's global multi-channel problem. We show that when an advertiser only optimizes over per-channel ROIs, her total conversion can be arbitrarily worse than what she could have obtained in the global problem. Further, we show that the advertiser can achieve the global optimal conversion when she only optimizes over per-channel budgets. In light of this finding, under a bandit feedback setting that mimics real-world scenarios where advertisers have limited information on ad auctions in each channels and how channels procure ads, we present an efficient learning algorithm that produces per-channel budgets whose resulting conversion approximates that of the global optimal problem. Finally, we argue that all our results hold for both single-item and multi-item auctions from which channels procure impressions on advertisers' behalf.