activity
20242026
collaborators

8 papers

cs.LG2026

Truthful Calibration Errors for Multi-Class Prediction

Yuxuan Lu, Yifan Wu, Jason Hartline +1

Calibrated predictions are useful because their numerical values can be interpreted as probabilities. Calibration errors are therefore widely used to evaluate, compare, and tune pr…

econ.TH2026

The Economics of No-regret Learning Algorithms

Jason Hartline

A fundamental challenge for modern economics is to understand what happens when actors in an economy are replaced with algorithms. Like rationality has enabled understanding of out…

cs.GT2025

Optimization of Scoring Rules

Jason D. Hartline, Yingkai Li, Liren Shan +1

We characterize the optimal reward functions (scoring rules) that incentivize an agent to acquire information and report it truthfully to the principal. The optimal scoring rules l…

cs.GT2025

A Geometric Analysis of Gains from Trade

Jason Hartline, Kangning Wang

We provide a geometric proof that the random proposer mechanism is a -approximation to the first-best gains from trade in bilateral exchange. We then refine this geometric analy…

cs.HC2025

Underspecified Human Decision Experiments Considered Harmful

Jessica Hullman, Alex Kale, Jason Hartline

Decision-making with information displays is a key focus of research in areas like human-AI collaboration and data visualization. However, what constitutes a decision problem, and…

cs.GT2025

Regulation of Algorithmic Collusion, Refined: Testing Pessimistic Calibrated Regret

Jason D. Hartline, Chang Wang, Chenhao Zhang

We study the regulation of algorithmic (non-)collusion amongst sellers in dynamic imperfect price competition by auditing their data as introduced by Hartline et al. [2024]. We dev…