# Knowledge-informed Bidding with Dual-process Control for Online Advertising

arXiv: https://arxiv.org/abs/2603.04920 · HTML: https://mlsanity.com/paper/2603.04920/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 25 of its 39 references that are in the map.
- First posted on arXiv 5 Mar 2026.

## Builds on (most cited first, 25 of 25)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [XGBoost: A Scalable Tree Boosting System](https://mlsanity.com/paper/1603.02754/) (2016)
- [Decision Transformer: Reinforcement Learning via Sequence Modeling](https://mlsanity.com/paper/2106.01345/) (2021)
- [Smart "Predict, then Optimize"](https://mlsanity.com/paper/1710.08005/) (2017)
- [Informed Machine Learning -- A Taxonomy and Survey of Integrating Knowledge into Learning Systems](https://mlsanity.com/paper/1903.12394/) (2019)
- [A Dual Process VLA: Efficient Robotic Manipulation Leveraging VLM](https://mlsanity.com/paper/2410.15549/) (2024)
- [Continuously Learning, Adapting, and Improving: A Dual-Process Approach to Autonomous Driving](https://mlsanity.com/paper/2405.15324/) (2024)
- [Bid Optimization by Multivariable Control in Display Advertising](https://mlsanity.com/paper/1905.10928/) (2019)
- [Planning Like Human: A Dual-process Framework for Dialogue Planning](https://mlsanity.com/paper/2406.05374/) (2024)
- [AuctionNet: A Novel Benchmark for Decision-Making in Large-Scale Games](https://mlsanity.com/paper/2412.10798/) (2024)
- [Generative Auto-Bidding with Value-Guided Explorations](https://mlsanity.com/paper/2504.14587/) (2025)
- [Feedback Control of Real-Time Display Advertising](https://mlsanity.com/paper/1603.01055/) (2016)
- [A Cooperative-Competitive Multi-Agent Framework for Auto-bidding in Online Advertising](https://mlsanity.com/paper/2106.06224/) (2021)
- [Real-Time Bidding Benchmarking with iPinYou Dataset](https://mlsanity.com/paper/1407.7073/) (2014)
- [Smooth Min-Max Monotonic Networks](https://mlsanity.com/paper/2306.01147/) (2023)
- [A framework for massive scale personalized promotion](https://mlsanity.com/paper/2108.12100/) (2021)
- [A Framework for Multi-stage Bonus Allocation in meal delivery Platform](https://mlsanity.com/paper/2202.10695/) (2022)
- [Improving deep learning with prior knowledge and cognitive models: A survey on enhancing explainability, adversarial robustness and zero-shot learning](https://mlsanity.com/paper/2403.07078/) (2024)
- [Safe Online Bid Optimization with Return on Investment and Budget Constraints](https://mlsanity.com/paper/2201.07139/) (2022)
- [A Unified Theory of Dual-Process Control](https://mlsanity.com/paper/2211.07036/) (2022)
- [Optimized Cost Per Click in Online Advertising: A Theoretical Analysis](https://mlsanity.com/paper/2405.14279/) (2024)
- [Safe and Adaptive Decision-Making for Optimization of Safety-Critical Systems: The ARTEO Algorithm](https://mlsanity.com/paper/2211.05495/) (2022)
- [Online Ad Procurement in Non-stationary Autobidding Worlds](https://mlsanity.com/paper/2307.05698/) (2023)
- [Enhancing Monotonic Modeling with Spatio-Temporal Adaptive Awareness in Diverse Marketing](https://mlsanity.com/paper/2406.14132/) (2024)
- [Learning Monotonic Probabilities with a Generative Cost Model](https://mlsanity.com/paper/2506.03542/) (2025)

## Abstract (arXiv)

Bid optimization in online advertising relies on black-box machine-learning models that learn bidding decisions from historical data. However, these approaches fail to replicate human experts' adaptive, experience-driven, and globally coherent decisions. Specifically, they generalize poorly in data-sparse cases because of missing structured knowledge, make short-sighted sequential decisions that ignore long-term interdependencies, and struggle to adapt in out-of-distribution scenarios where human experts succeed. To address this, we propose KBD (Knowledge-informed Bidding with Dual-process control), a novel method for bid optimization. KBD embeds human expertise as inductive biases through the informed machine-learning paradigm, uses Decision Transformer (DT) to globally optimize multi-step bidding sequences, and implements dual-process control by combining a fast rule-based PID (System 1) with DT (System 2). Extensive experiments highlight KBD's advantage over existing methods and underscore the benefit of grounding bid optimization in human expertise and dual-process control.