mlsanityData to 14 Oct 2026

VAO: Validation-Aligned Optimization for Cross-Task Generative Auto-Bidding

arXiv 2510.07760 ↗First posted 9 Oct 2025cs.LG cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Generative auto-bidding has demonstrated strong performance in online advertising, yet it often suffers from data scarcity in small-scale settings with limited advertiser participation. While cross-task data sharing is a natural remedy to mitigate this issue, naive approaches often introduce gradient bias due to distribution shifts across different tasks, and existing methods are not readily applicable to generative auto-bidding. In this paper, we propose Validation-Aligned Optimization (VAO), a principled data-sharing method that adaptively reweights cross-task data contributions based on validation performance feedback. Notably, VAO aligns training dynamics to prioritize updates that improve generalization on the target task, effectively leveraging auxiliary data and mitigating gradient bias. Building on VAO, we introduce a unified generative autobidding framework that generalizes across multiple tasks using a single model and all available task data. Extensive experiments on standard auto-bidding benchmarks validate the effectiveness of our approach.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 38 of its 58 references that are in the map. First posted on arXiv 9 Oct 2025.

Builds on

38 of 58 references.

References · 38

  1. 2017FiLM: Visual Reasoning with a General Conditioning Layercited by 2,333
  2. 2017Gradient Episodic Memory for Continual Learningcited by 1,898
  3. 2020Conservative Q-Learning for Offline Reinforcement Learningcited by 1,809
  4. 2017Multi-Task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semanticscited by 1,358
  5. 2021Offline Reinforcement Learning with Implicit Q-Learningcited by 1,293
  6. 2020Gradient Surgery for Multi-Task Learningcited by 1,256
  7. 2018Off-Policy Deep Reinforcement Learning without Explorationcited by 1,241
  8. 2017GradNorm: Gradient Normalization for Adaptive Loss Balancing in Deep Multitask Networkscited by 834
  9. 2018Multi-Task Learning as Multi-Objective Optimizationcited by 821
  10. 2018End-to-End Multi-Task Learning with Attentioncited by 534
  11. 2016Cross-stitch Networks for Multi-task Learningcited by 467
  12. 2021Conflict-Averse Gradient Descent for Multi-task Learningcited by 459
26 more
  1. 2021MT-Opt: Continuous Multi-Task Robotic Reinforcement Learning at Scalecited by 229
  2. 2022Multi-Task Learning as a Bargaining Gamecited by 215
  3. 2020Just Pick a Sign: Optimizing Deep Multitask Models with Gradient Sign Dropoutcited by 201
  4. 2019AdaShare: Learning What To Share For Efficient Deep Multi-Task Learningcited by 160
  5. 2017Online Learning Rate Adaptation with Hypergradient Descentcited by 118
  6. 2021Reasonable Effectiveness of Random Weighting: A Litmus Test for Multi-Task Learningcited by 101
  7. 2020Offline Meta-Reinforcement Learning with Advantage Weightingcited by 93
  8. 2023FAMO: Fast Adaptive Multitask Optimizationcited by 78
  9. 2023Data Quality in Imitation Learningcited by 75
  10. 2021Conservative Data Sharing for Multi-Task Offline Reinforcement Learningcited by 64
  11. 2022How to Leverage Unlabeled Data in Offline Reinforcement Learningcited by 62
  12. 2018Budget Constrained Bidding by Model-free Reinforcement Learning in Display Advertisingcited by 61
  13. 2020Online Learning with Imperfect Hintscited by 37
  14. 2024Fair Resource Allocation in Multi-Task Learningcited by 35
  15. 2022Sustainable Online Reinforcement Learning for Auto-biddingcited by 29
  16. 2020Knowledge Transfer in Multi-Task Deep Reinforcement Learning for Continuous Controlcited by 28
  17. 2024AuctionNet: A Novel Benchmark for Decision-Making in Large-Scale Gamescited by 28
  18. 2022Cross-Task Knowledge Distillation in Multi-Task Recommendationcited by 22
  19. 2024Doubly Mild Generalization for Offline Reinforcement Learningcited by 21
  20. 2021Model-based Meta Reinforcement Learning using Graph Structured Surrogate Modelscited by 17
  21. 2024Offline Reinforcement Learning with OOD State Correction and OOD Action Suppressioncited by 17
  22. 2024GO4Align: Group Optimization for Multi-Task Alignmentcited by 11
  23. 2023Episodic Multi-Task Learning with Heterogeneous Neural Processescited by 8
  24. 2024Pessimistic Value Iteration for Multi-Task Data Sharing in Offline Reinforcement Learningcited by 7
  25. 2024GAS: Generative Auto-bidding with Post-training Searchcited by 6
  26. 2025Enhancing Generative Auto-bidding with Offline Reward Evaluation and Policy Searchcited by 1

Built on by

Not cited yet.