{"ID":6023365,"CreatedAt":"2026-07-08T01:00:23.257252134Z","UpdatedAt":"2026-07-10T04:00:09.368444197Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2607.05813","arxiv_id":"2607.05813","title":"Contextual Procurement Auctions with Bandit Learning","abstract":"We study repeated contextual procurement auctions in which the platform must learn context-dependent product values from bandit feedback. We give an exactly truthful explore-then-commit mechanism with $\\widetilde O((ng)^{1/3}T^{2/3})$ regret. We also give a frozen-payment UCB mechanism with a regret-incentive tradeoff: the near-UCB tuning attains \\(\\widetilde O(\\sqrt{ngT})\\) welfare regret, while for fixed \\(n,g\\) its total incentive error is \\(\\widetilde O(T^{3/4})\\); the balanced tuning gives \\(\\widetilde O(T^{2/3})\\) on both scales. Regret is measured as welfare loss relative to the full-information efficient allocation. We prove a matching lower bound for the frozen-payment regret-incentive tradeoff.","short_abstract":"We study repeated contextual procurement auctions in which the platform must learn context-dependent product values from bandit feedback. We give an exactly truthful explore-then-commit mechanism with $\\widetilde O((ng)^{1/3}T^{2/3})$ regret. We also give a frozen-payment UCB mechanism with a regret-incentive tradeoff:...","url_abs":"https://arxiv.org/abs/2607.05813","url_pdf":"https://arxiv.org/pdf/2607.05813v1","authors":"[\"Yiling Chen\",\"Shi Feng\",\"Sadie Zhao\"]","published":"2026-07-07T04:18:18Z","proceeding":"cs.GT","tasks":"[\"cs.GT\",\"cs.LG\"]","methods":"[]","has_code":false}