cs.GTFeb 12, 2026

Is Online Linear Optimization Sufficient for Strategic Robustness?

Authors: Yang Cai, Haipeng Luo, Chen-Yu Wei, Weiqiang Zheng

Organizations: Yale University. · University of Southern California. · University of Virginia.

Abstract

We consider bidding in repeated Bayesian first-price auctions. Bidding algorithms that achieve optimal regret have been extensively studied, but their strategic robustness to the seller's manipulation remains relatively underexplored. Bidding algorithms based on no-swap-regret algorithms achieve both desirable properties, but are suboptimal in terms of statistical and computational efficiency. In contrast, online gradient ascent is the only algorithm that achieves O(TK)O(\sqrt{TK}) regret and strategic robustness [KSS24], where TT denotes the number of auctions and KK the number of bids. In this paper, we explore whether simple online linear optimization (OLO) algorithms suffice for bidding algorithms with both desirable properties. Our main result shows that sublinear linearized regret is sufficient for strategic robustness. Specifically, we construct simple black-box reductions that convert any OLO algorithm into a strategically robust no-regret bidding algorithm, in both known and unknown value distribution settings. For the known value distribution case, our reduction yields a bidding algorithm that achieves O(Tlog⁡K)O(\sqrt{T \log K}) regret and strategic robustness (with exponential improvement on the KK-dependence compared to [KSS24]). Moreover, we can further exploit the single-strategy benchmark and construct a bidding algorithm with O(T(log⁡K+log⁡T))O(\sqrt{T(\log K+\log T)}) regret and O(1)O(1) strategic robustness. For the unknown value distribution case, our reduction gives a bidding algorithm with high-probability O(T(log⁡K+log⁡(T/δ))O(\sqrt{T (\log K+\log(T/δ)}) regret and strategic robustness, while removing the bounded density assumption made in [KSS24].

Figures & tables

Explore similar work

CardsList
  1. Impossibility of No-Regret in Multi-Agent Bidding

    Oct 27, 2026Zongjun Yang, Rachitesh Kumar, Christian KroerRegret MinimizationAutomated Bidding

  2. A3M: Adaptive, Adversarial and Multi-Objective Learning for Strategic Bidding in Repeated Auctions

    Jun 27, 2026Junhan Li, Yuxin Zhang, Haoran Wang +1Multi-Objective Reinforcement LearningGame Theory

  3. Do Not Trust The Auctioneer: Learning to Bid in Feedback-Manipulated Auctions

    May 21, 2026Luigi Foscari, Matilde Tullii, Vianney PerchetGame TheoryAutomated Bidding