Enregistré dans:
| Auteurs principaux: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | https://arxiv.org/abs/2508.08687 |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866911118400684032 |
|---|---|
| author | Peng, Yunshan Shu, Wenzheng Sun, Jiahao Zeng, Yanxiang Pang, Jinan Bai, Wentao Bai, Yunke Liu, Xialong Jiang, Peng |
| author_facet | Peng, Yunshan Shu, Wenzheng Sun, Jiahao Zeng, Yanxiang Pang, Jinan Bai, Wentao Bai, Yunke Liu, Xialong Jiang, Peng |
| contents | Auto-bidding is widely used in advertising systems, serving a diverse range of advertisers. Generative bidding is increasingly gaining traction due to its strong planning capabilities and generalizability. Unlike traditional reinforcement learning-based bidding, generative bidding does not depend on the Markov Decision Process (MDP), thereby exhibiting superior planning performance in long-horizon scenarios. Conditional diffusion modeling approaches have shown significant promise in the field of auto-bidding. However, relying solely on return as the optimality criterion is insufficient to guarantee the generation of truly optimal decision sequences, as it lacks personalized structural information. Moreover, the auto-regressive generation mechanism of diffusion models inherently introduces timeliness risks. To address these challenges, we introduce a novel conditional diffusion modeling approach that integrates expert trajectory guidance with a skip-step sampling strategy to improve generation efficiency. The efficacy of this method has been demonstrated through comprehensive offline experiments and further substantiated by statistically significant outcomes in online A/B testing, yielding an 11.29% increase in conversions and a 12.36% growth in revenue relative to the baseline. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_08687 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Expert-Guided Diffusion Planner for Auto-Bidding Peng, Yunshan Shu, Wenzheng Sun, Jiahao Zeng, Yanxiang Pang, Jinan Bai, Wentao Bai, Yunke Liu, Xialong Jiang, Peng Machine Learning Information Retrieval Auto-bidding is widely used in advertising systems, serving a diverse range of advertisers. Generative bidding is increasingly gaining traction due to its strong planning capabilities and generalizability. Unlike traditional reinforcement learning-based bidding, generative bidding does not depend on the Markov Decision Process (MDP), thereby exhibiting superior planning performance in long-horizon scenarios. Conditional diffusion modeling approaches have shown significant promise in the field of auto-bidding. However, relying solely on return as the optimality criterion is insufficient to guarantee the generation of truly optimal decision sequences, as it lacks personalized structural information. Moreover, the auto-regressive generation mechanism of diffusion models inherently introduces timeliness risks. To address these challenges, we introduce a novel conditional diffusion modeling approach that integrates expert trajectory guidance with a skip-step sampling strategy to improve generation efficiency. The efficacy of this method has been demonstrated through comprehensive offline experiments and further substantiated by statistically significant outcomes in online A/B testing, yielding an 11.29% increase in conversions and a 12.36% growth in revenue relative to the baseline. |
| title | Expert-Guided Diffusion Planner for Auto-Bidding |
| topic | Machine Learning Information Retrieval |
| url | https://arxiv.org/abs/2508.08687 |