Budget Pacing in Repeated Auctions: Regret and Efficiency without Convergence

@article{Gaitonde2022BudgetPI,
  title={Budget Pacing in Repeated Auctions: Regret and Efficiency without Convergence},
  author={Jason Gaitonde and Yingkai Li and Bar Light and Brendan Lucier and Aleksandrs Slivkins},
  journal={ArXiv},
  year={2022},
  volume={abs/2205.08674}
}
We study the aggregate welfare and individual regret guarantees of dynamic pacing algorithms in the context of repeated auctions with budgets. Such algorithms are commonly used as bidding agents in Internet advertising platforms, adaptively learning to shade bids in order to match a specified spend target. We show that when agents simultaneously apply a natural form of gradient-based pacing, the liquid welfare obtained over the course of the learning dynamics is at least half the optimal… 
2 Citations

Dynamic Budget Throttling in Repeated Second-Price Auctions

This paper proposes the OGD-CB algorithm, which involves simultaneous distribution learning and revenue optimization facing online ad queries, and demonstrates that this algorithm guarantees an O ( √ T log T ) regret with probability 1 − O (1 /T ) relative to the fluid adaptive throttling benchmark.

No-regret Learning in Repeated First-Price Auctions with Budget Constraints

This paper proposes an RL-based bidding algorithm against the optimal non-anticipating strategy under stationary competition and obtains e O ( √ T ) -regret if the bids are all revealed at the end of each round.

References

SHOWING 1-10 OF 47 REFERENCES

Autobidding with Constraints

The novel contribution is to show a strong connection between bidding and auction design, in that the bidding formula is optimal if and only if the underlying auction is truthful.

Bandits with Global Convex Constraints and Objective

A model for capturing the exploration–exploitation trade-off inherent in many sequential decision-making problems and the classic MAB framework only allows for one-size-fits-all solutions.

Learning in Repeated Auctions with Budgets: Regret Minimization and Equilibrium

A family of dynamic bidding strategies, referred to as "adaptive pacing" strategies, in which advertisers adjust their bids throughout the campaign according to the sample path of observed expenditures are introduced, which constitute an approximate Nash equilibrium in dynamic strategies.

Resourceful Contextual Bandits

This work designs the first algorithm for solving contextual bandits with ancillary constraints on resources that handles constrained resources other than time, and improves over a trivial reduction to the non-contextual case.

Introduction to Online Convex Optimization

  • Elad Hazan
  • Computer Science
    Found. Trends Optim.
  • 2016
This monograph portrays optimization as a process, by applying an optimization method that learns as one goes along, learning from experience as more aspects of the problem are observed.

Budget Management Strategies in Repeated Auctions

The study sheds light on the impact of budget management strategies on the tradeoff between the seller's profit and buyers' utility and empirically compare the system equilibria of these strategies using real ad auction data in sponsored search and randomly generated bids.

US digital ad spending 2019

  • 2019

US digital ad spending

  • 2019

Us digital ad spending 2019, Mar 2019

  • URL https://www.emarketer.com/content/us-digital-ad-spending-2019
  • 2019

Non-quasi-linear Agents in Quasi-linear Mechanisms

It is shown that any mechanism that is truthful for quasi-linear buyers has a simple best response function for buyers with non-linear disutility from payments, and it is proved the existence of a Nash equilibrium in which agents use ROI-optimal strategies for a general class of allocation problems.