Constrained Auto-Bidding via Generative Response Modeling
For advertisers using auto-bidding systems, this work provides a method that better handles non-stationarity and constraint satisfaction, though improvements are incremental over existing approaches.
The paper tackles the problem of auto-bidding under budget and ratio constraints with non-stationary traffic. It proposes the Generative Response Model (GRM), which predicts future traffic and cost/value curves, enabling a lightweight analytic controller that improves constraint stability and overall score over baselines on AuctionNet.
Auto-bidding systems aim to maximize advertiser value over long horizons under budget constraints and ratio targets such as cost-per-acquisition, yet future traffic and auction dynamics are non-stationary and uncertain. Existing approaches face distinct limitations: control-based pacing reacts to deviations but cannot anticipate future conditions, while RL and generative methods fold constraints into reward signals, obscuring violations and degrading under distribution shift. We shift the learning target from actions to responses with the Generative Response Model (GRM), a history-conditioned sequence model that jointly predicts future traffic volume and horizon-aggregate cost/value curves as functions of a single bid multiplier. We show that under mild monotonicity conditions, the optimality gap relative to full per-tick control is bounded by the dispersion of per-tick marginal value-per-cost. Given predicted responses, a lightweight analytic controller enforces each active constraint via a 1D root-finding step. We prove this controller is exact for the single-multiplier problem and bound constraint violations under receding-horizon replanning in terms of prediction error. Experiments on AuctionNet show that GRM improves constraint stability and overall score compared to existing baselines.