Search papers, labs, and topics across Lattice.
This paper introduces SWAG-Bid, a hierarchical framework for auto-bidding that optimizes advertising effectiveness by considering multiple overlapping evaluation windows rather than treating each day as an independent episode. By employing a Masked Trajectory Model for market forecasting and Multi-Window Model Predictive Control Sampling (MWMS) for scoring candidate plans, the approach effectively anticipates future market conditions and adjusts bidding strategies accordingly. Experiments demonstrate that SWAG-Bid not only meets efficiency constraints but also enhances value acquisition, outperforming traditional methods in real-world settings like AliExpress.
SWAG-Bid redefines auto-bidding by integrating long-term market forecasting and adaptive control, leading to superior advertising outcomes.
Auto-bidding systems optimize bids to maximize value under efficiency constraints such as Cost-Per-Action (CPA). Existing methods treat each day as an independent episode. However, many advertisers produce value so sparsely that per-day efficiency ratios become statistically unreliable, undermining advertiser retention. Platforms therefore evaluate window-level efficiency over sliding windows of $W{=}7$ days, ensuring fair evaluation and long-term advertising effectiveness. This creates cross-episode coupling: each day's bidding decisions affect up to $W$ overlapping windows, so setting daily targets requires anticipating future market conditions. We propose SWAG-Bid (Sliding-Window Aware Generative Auto-Bidding), a hierarchical framework decomposing this challenge into episode-level planning and step-level execution. The planner uses a Masked Trajectory Model to forecast markets and generate candidate plans, scored across all overlapping windows by Multi-Window Model Predictive Control Sampling (MWMS) with exponential confidence decay. The controller adjusts reliance on this guidance through a state-adaptive gate, Per-Step Gated Adaptive Layer Normalization (PSG-AdaLN), complemented by Return-to-Go and Cost-to-Go channels carrying budget and constraint information. Experiments on AuctionNet-Sparse and online A/B tests on AliExpress show that SWAG-Bid achieves competitive constraint satisfaction and value acquisition under sliding-window evaluation.
DAMO