The paper tackles the data market design problem, which seeks signaling schemes that maximize revenue for an information seller. It applies deep learning to learn these schemes, addressing both obedience and incentive constraints, and demonstrates that the framework can replicate known theoretical solutions, extend to more complex scenarios, and suggest new optimal designs. The study builds on prior auction‑design work and introduces a novel approach for revenue‑optimal data markets.
By Sai Srivatsa Ravindranath, Yanchen Jiang, David C. Parkes
arXiv:2607. 01185v1 Announce Type: new Abstract: Combinatorial optimization (CO) problems are difficult because certifiable discrete structure induces exponential search.
By Jingyi Chen, Xinyuan Zhang, Xinwu Qian
arXiv:2606. 28943v1 Announce Type: cross Abstract: Learning to bid in repeated multi-unit auctions with bandit feedback poses a fundamental challenge.
By Junhan Li, Yuxin Zhang, Haoran Wang, Minghao Chen
The paper introduces Correlation-Aware Affine Maximizer Auctions (CA-AMA), a new framework that extends traditional AMAs by incorporating a correlation-aware payment structure. CA-AMA maintains dominant-strategy incentive compatibility and is formulated as a constraint optimization problem with individual rationality constraints. The authors theoretically demonstrate that CA-AMA can achieve optimal revenue in scenarios where classic AMAs perform poorly, and they present a practical two-stage training algorithm that empirically finds near-optimal CA-AMA solutions with improved revenue and minimal IR violations.
By Haoran Sun, Xuanzhi Xia, Xu Chu, Xiaotie Deng
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.
By Negin Golrezaei, Sourav Sahoo
We study repeated bidding in multi-unit discriminatory (pay-as-bid) auctions for a single bidder with per-round utility equal to value minus $α$ times payment, where $α\in[0,1]$ is a cost-of-capital parameter. The bidder aims to maximize cumulative utility over $T$ rounds subject to a total budget $B$.
arXiv:2609.33289v2 Announce Type: replace
Abstract: Autonomous large language model (LLM) agents operating in multi-product markets must make sequential decisions under information asymmetry and reso...
By Shuze Daniel Liu, Claire Chen, Jiuqi Wang, David Simchi-Levi, Thorsten Joachims
CG4AI is a column generation framework that trains AI models while enforcing linear constraints on their outputs. It constructs a convex combination of models, using a master linear program to set mixture weights and a pricing subproblem to generate new models guided by dual variables, focusing on the most violated constraints. The method is applied to MNIST digit classification—demonstrating constraint learning, adversarial robustness, error correction, and output relabeling—and to multi‑commodity flow routing, achieving feasible predictors with higher accuracy than single‑model baselines.
By Youcef Magnouche, Abderrahmane Driouch, S\'ebastien Martin, Pierre Bauguion
arXiv:2607. 13373v1 Announce Type: cross Abstract: Column generation (CG) is central to many large-scale optimization algorithms, including branch-price-and-cut methods for vehicle routing problems, but unstable dual solutions can substantially slow its convergence.
By Zhengzhong Ricky You, Bo Tang, Haoran Liu, Baichuan Mo
arXiv:2608.24743v1 Announce Type: new
Abstract: Existing linear program (LP) and semidefinite program (SDP) relaxations for rectified linear unit (ReLU) neural network (NN) verification yield overly-...
By Hanna Jiamei Zhang, Alan Papalia, Michael Everett, David M. Rosen
arXiv:2608. 02343v1 Announce Type: cross Abstract: Many operational problems are constrained sequential decision processes with large, combinatorial action spaces and interdependent feasibility constraints.
By Patrick Helm, Jan-Niklas Doerr, Joren Gijsbrechts, Stefan Minner
arXiv:2606. 18111v1 Announce Type: cross Abstract: Fairness is an important aspect of decision-making in multi-objective reinforcement learning (MORL), where policies must ensure both optimality and equity across multiple, potentially conflicting objectives.
By Umer Siddique, Peilang Li, Yongcan Cao