In recent years, machine learning has been called upon to solve increasingly more complex tasks and to regulate many aspects of our social, economic, and technological world. These applications include learning economic policies from data, prediction in financial markets, learning personalize models across population of users, and ranking qualified candidates for admission, hiring, and lending. These tasks take place in a complex social and economic context where the learners and objects of learning are often people or organizations that are impacted by the learning algorithm and, in return, can take actions that influence the learning process. Learning in this context calls for a new vision for machine learning and economics that aligns the incentives and interests of the learners and other parties and is robust to the evolving social and economic needs. This workshop explores a view of machine learning and economics that considers interactions of learning systems with a wide range of social and strategic behaviors. Examples of these problems include: multi-agent learning systems, welfare-aware machine learning, learning from strategic and economic data, learning as a behavioral model, and causal inference for learning impact of strategic choices.
| Opening remarks (Remarks) | |
| Keynote: Michael I. Jordan (On Dynamics-Informed Blending of Machine Learning and Game Theory) (Keynote) | |
| Keynote: Susan Athey (Machine Learning with Strategic Agents: Lessons from Incentive Theory and Econometrics) (Keynote) | |
| Discussion with Michael Jordan and Susan Athey, moderated by Kevin Leyton-Brown (Discussion Panel) | |
| Spotlight 1: Exploration and Incentives in Reinforcement Learning (Spotlights) | |
| Q&A for Spotlight 1 (Q&A) | |
| Spotlight 2: Models of fairness in federated learning (Spotlights) | |
| Q&A for Spotlight 2 (Q&A) | |
| Spotlight 3: Efficient Competitions and Online Learning with Strategic Forecasters (Spotlights) | |
| Q&A for Spotlight 3 (Q&A) | |
| Spotlight 4: Estimation of Standard Asymmetric Auction Models (Spotlights) | |
| Q&A for Spotlight 4 (Q&A) | |
| Spotlight 5: Strategic clustering (Spotlights) | |
| Q&A for Spotlight 5 (Q&A) | |
| Poster Session | |
| Keynote: Dorsa Sadigh (Theory and Practice of Partner-Aware Algorithms in Multi-Agent Coordination) (Keynote) | |
| Keynote: Vince Conitzer (Automated Mechanism Design for Strategic Classification) (Keynote) | |
| Discussion with Dorsa Sadigh and Vincent Conitzer, moderated by Peter Stone (Discussion Panel) | |
| Concluding Remarks (Remarks) | |
| Normative disagreement as a challenge for Cooperative AI (Oral) | |
| Learning through Recourse under Censoring (Oral) | |
| Pessimistic Offline Reinforcement Learning with Multiple Agents (Oral) | |
| Promoting Resilience of Multi-Agent Reinforcement Learning via Confusion-Based Communication (Oral) | |
| Game Redesign in No-regret Game Playing (Oral) | |
| Pseudo-Competitive Games and Algorithmic Pricing (Oral) | |
| Learning in Matrix Games can be Arbitrarily Complex (Oral) | |
| Test-optional Policies: Overcoming Strategic Behavior and Informational Gaps (Oral) | |
| Models of fairness in federated learning (Oral) | |
| Improving Robustness of Malware Classifiers using Adversarial Strings Generated from Perturbed Latent Representations (Oral) | |
| Improving Fairness in Credit Lending Models using Subgroup Threshold Optimization (Oral) | |
| The Platform Design Problem (Oral) | |
| Strategic Classification in the Dark (Oral) | |
| Strategic Classification Made Practical (Oral) | |
| Nash Convergence of Mean-Based Learning Algorithms in First Price Auctions (Oral) | |
| Bayesian Persuasion for Algorithmic Recourse (Oral) | |
| Reward-Free Attacks in Multi-Agent Reinforcement Learning (Oral) | |
| Reward Poisoning in Reinforcement Learning: Attacks Against Unknown Learners in Unknown Environments (Oral) | |
| Global Convergence of Multi-Agent Policy Gradient in Markov Potential Games (Oral) | |
| Exploration-Exploitation in Multi-Agent Competition: Convergence with Bounded Rationality (Oral) | |
| Timing is Money: The Impact of Arrival Order in Beta-Bernoulli Prediction Markets (Oral) | |
| The Price of Incentivizing Exploration: A Characterization via Thompson Sampling and Sample Complexity (Oral) | |
| Negotiating networks in oligopoly markets for price sensitive products (Oral) | |
| Approximating Bayes Nash Equilibria in Auction Games via Gradient Dynamics (Oral) | |
| Coopetition Against an Amazon (Oral) | |
| Exploration and Incentives in Reinforcement Learning (Oral) | |
| Regret, stability, and fairness in matching markets with bandit learners (Oral) | |
| Scoring Rules for Performative Binary Prediction (Oral) | |
| Efficient Competitions and Online Learning with Strategic Forecasters (Poster) | |
| Alternative Microfoundations for Strategic Classification (Oral) | |
| Estimation of Standard Asymmetric Auction Models (Oral) | |
| Near-Optimal No-Regret Learning in General Games (Oral) | |
| Bounded Rationality for Multi-Agent Motion Planning and Behavior Learning (Oral) | |
| Information Discrepancy in Strategic Learning (Oral) | |
| When to Call Your Neighbor? Strategic Communication in Cooperative Stochastic Bandits (Oral) | |
| Gaming Helps! Learning from Strategic Interactions in Natural Dynamics (Oral) | |
| Interactive Robust Policy Optimization for Multi-Agent Reinforcement Learning (Oral) | |
| Strategic clustering (Oral) | |
| One for One, or All for All: Equilibria and Optimality of Collaboration in Federated Learning (Oral) | |
| On classification of strategic agents who can both game and improve (Oral) | |
| The Strategic Perceptron (Oral) | |
| Price Discovery and Efficiency in Waiting Lists: A Connection to Stochastic Gradient Descent (Oral) | |
| Unfairness Despite Awareness: Group-Fair Classification with Strategic Agents (Oral) | |
| Learning Losses for Strategic Classification (Oral) | |