Algorithmic Principles For Multiclass Learning Are Hard To Come By: Limits of Regularization and Proper Learning [arXiv]
Manuscript 2026
Writings
(α-β) indicates alphabetical order; * indicates equal contribution.
The Computable but Not Learnable Information-Value-Free Equilibria and Regulation of Algorithmic Collusion [arXiv]
EC 2026 27th ACM Conference on Economics and Computation. A preliminary poster appeared in the 5th ACM Symposium on Computer Science and Law.
Regulation of Algorithmic Collusion, Refined: Testing Pessimistic Calibrated Regret [arXiv] [conference article]
CS&Law 2025 4th ACM Symposium on Computer Science and Law. A preliminary version appeared in the 2nd Workshop on Regulatable ML @NeurIPS'24.
Dynamic Budget Throttling in Repeated Second-Price Auctions [arXiv] [conference article]
AAAI 2024 The 38th Annual AAAI Conference on Artificial Intelligence
Budget-Constrained Auctions with Unassured Priors: Strategic Equivalence and Structural Properties [arXiv] [conference article]
WWW 2024 The 2024 ACM Web Conference Oral presentation
Contextual Decision-Making with Knapsacks beyond the Worst Case [arXiv] [conference article]
NeurIPS 2024 The 38th Annual Conference on Neural Information Processing Systems