arXiv Machine Learning
Robust Budget Pacing with a Single Sample
Read the original on arXiv Machine Learning →The Flow has not summarised this story yet — read it at arXiv Machine Learning.
Related stories
arXiv Machine Learning
Sep 22
Plan-Driven Adaptive Bidding for First-Price Auctions with Budget Constraints under Nonstationarity
arXiv:2505.02796v3 Announce Type: replace-cross Abstract: We study budget pacing in repeated first-price auctions when an advertiser's private-value distributions change over time and the stationary...
arXiv Machine Learning
Aug 31
Budget-Constrained Causal Bandits: Bridging Uplift Modeling and Sequential Decision-Making
The paper introduces Budget-Constrained Causal Bandits (BCCB), an online framework that learns individual treatment effects, explores uncertain users, and manages budget pacing simultaneously. It derives a per-arrival decision rule from a KKT condition of a Lagrangian relaxation, providing a principled algorithmic foundation. Experiments on the Criteo Uplift dataset show BCCB outperforms offline pipelines and other online baselines, especially when historical data is scarce (below 7,500 observations).
arXiv Machine Learning
Aug 18
Dynamic Pricing and Advertising with Demand Learning
arXiv:2304. 14385v4 Announce Type: replace-cross Abstract: We consider a novel pricing and advertising framework in which a seller not only sets the product price but also designs flexible advertising schemes to influence customers' valuations of the product.
arXiv Machine Learning
22h ago
Online Generalized-Mean Welfare Maximization: Achieving Near-Optimal Regret from Samples
The paper investigates online fair allocation of sequential items to agents with heterogeneous preferences, aiming to maximize generalized-mean welfare. In an i.i.d. arrival setting, a pure greedy algorithm achieves near-optimal “~O(1/T)” average regret without needing distributional knowledge. For nonstationary arrivals, the authors show that a single historical sample per distribution suffices to recover the same regret rate, using re-solving algorithms that remain robust to distribution shifts.
arXiv Machine Learning
Aug 18
Learning to Bid with Unknown Private Values in Budget-Constrained First-Price Auctions
arXiv:2605. 09448v2 Announce Type: replace Abstract: We study the operational problem of automated bidding in repeated first-price auctions under budget and return-on-spend (RoS) constraints.
arXiv Machine Learning
Jun 30
Learning to Bid in Discriminatory Auctions with Budget Constraints
arXiv:2606. 29252v1 Announce Type: new Abstract: We study repeated bidding in multi-unit discriminatory (pay-as-bid) auctions for a single bidder with per-round utility equal to value minus $\alpha$ times payment, where $\alpha\in[0,1]$ is a cost-of-capital parameter.