Workshop
Learning in Presence of Strategic Behavior
Omer Ben-Porat · Nika Haghtalab · Annie Liang · Yishay Mansour · David Parkes
Mon 13 Dec, 8:50 a.m. PST
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.
Schedule
Mon 8:50 a.m. - 9:00 a.m.
|
Opening remarks
(
Remarks
)
>
SlidesLive Video |
🔗 |
Mon 9:00 a.m. - 9:40 a.m.
|
Keynote: Michael I. Jordan (On Dynamics-Informed Blending of Machine Learning and Game Theory)
(
Keynote
)
>
SlidesLive Video |
🔗 |
Mon 9:40 a.m. - 10:20 a.m.
|
Keynote: Susan Athey (Machine Learning with Strategic Agents: Lessons from Incentive Theory and Econometrics)
(
Keynote
)
>
SlidesLive Video |
🔗 |
Mon 10:20 a.m. - 10:50 a.m.
|
Discussion with Michael Jordan and Susan Athey, moderated by Kevin Leyton-Brown
(
Discussion Panel
)
>
SlidesLive Video |
🔗 |
Mon 11:10 a.m. - 11:17 a.m.
|
Spotlight 1: Exploration and Incentives in Reinforcement Learning
(
Spotlights
)
>
SlidesLive Video |
Max Simchowitz · Aleksandrs Slivkins 🔗 |
Mon 11:17 a.m. - 11:20 a.m.
|
Q&A for Spotlight 1
(
Q&A
)
>
|
🔗 |
Mon 11:20 a.m. - 11:27 a.m.
|
Spotlight 2: Models of fairness in federated learning
(
Spotlights
)
>
SlidesLive Video |
Kate Donahue · Jon Kleinberg 🔗 |
Mon 11:27 a.m. - 11:30 a.m.
|
Q&A for Spotlight 2
(
Q&A
)
>
|
🔗 |
Mon 11:30 a.m. - 11:37 a.m.
|
Spotlight 3: Efficient Competitions and Online Learning with Strategic Forecasters
(
Spotlights
)
>
SlidesLive Video |
Anish Thilagar · Rafael Frongillo · Bo Waggoner · Robert Gomez 🔗 |
Mon 11:37 a.m. - 11:40 a.m.
|
Q&A for Spotlight 3
(
Q&A
)
>
|
🔗 |
Mon 11:40 a.m. - 11:47 a.m.
|
Spotlight 4: Estimation of Standard Asymmetric Auction Models
(
Spotlights
)
>
SlidesLive Video |
Yeshwanth Cherapanamjeri · Constantinos Daskalakis · Andrew Ilyas · Emmanouil Zampetakis 🔗 |
Mon 11:47 a.m. - 11:50 a.m.
|
Q&A for Spotlight 4
(
Q&A
)
>
|
🔗 |
Mon 11:50 a.m. - 11:57 a.m.
|
Spotlight 5: Strategic clustering
(
Spotlights
)
>
SlidesLive Video |
Ana-Andreea Stoica · Christos Papadimitriou 🔗 |
Mon 11:57 a.m. - 12:00 p.m.
|
Q&A for Spotlight 5
(
Q&A
)
>
|
🔗 |
Mon 12:00 p.m. - 1:00 p.m.
|
Poster Session ( Poster Session ) > link | 🔗 |
Mon 1:00 p.m. - 1:40 p.m.
|
Keynote: Dorsa Sadigh (Theory and Practice of Partner-Aware Algorithms in Multi-Agent Coordination)
(
Keynote
)
>
SlidesLive Video |
🔗 |
Mon 1:40 p.m. - 2:20 p.m.
|
Keynote: Vince Conitzer (Automated Mechanism Design for Strategic Classification)
(
Keynote
)
>
SlidesLive Video |
🔗 |
Mon 2:20 p.m. - 2:50 p.m.
|
Discussion with Dorsa Sadigh and Vincent Conitzer, moderated by Peter Stone
(
Discussion Panel
)
>
SlidesLive Video |
🔗 |
Mon 2:50 p.m. - 3:00 p.m.
|
Concluding Remarks
(
Remarks
)
>
SlidesLive Video |
🔗 |
-
|
Efficient Competitions and Online Learning with Strategic Forecasters ( Poster ) > link | Anish Thilagar · Rafael Frongillo · Bo Waggoner · Robert Gomez 🔗 |
-
|
Alternative Microfoundations for Strategic Classification ( Oral ) > link | Meena Jagadeesan · Celestine Mendler-DĂĽnner · Moritz Hardt 🔗 |
-
|
Estimation of Standard Asymmetric Auction Models ( Oral ) > link | Yeshwanth Cherapanamjeri · Constantinos Daskalakis · Andrew Ilyas · Emmanouil Zampetakis 🔗 |
-
|
Near-Optimal No-Regret Learning in General Games ( Oral ) > link | Constantinos Daskalakis · Maxwell Fishelson · Noah Golowich 🔗 |
-
|
Bounded Rationality for Multi-Agent Motion Planning and Behavior Learning ( Oral ) > link | Junhong Xu · Kai Yin · Lantao Liu 🔗 |
-
|
Information Discrepancy in Strategic Learning ( Oral ) > link | Yahav Bechavod · Chara Podimata · Steven Wu · Juba Ziani 🔗 |
-
|
When to Call Your Neighbor? Strategic Communication in Cooperative Stochastic Bandits ( Oral ) > link | Udari Madhushani · Naomi Leonard 🔗 |
-
|
Gaming Helps! Learning from Strategic Interactions in Natural Dynamics ( Oral ) > link | Yahav Bechavod · Katrina Ligett · Steven Wu · Juba Ziani 🔗 |
-
|
Interactive Robust Policy Optimization for Multi-Agent Reinforcement Learning ( Oral ) > link | Videh Nema · Balaraman Ravindran 🔗 |
-
|
Negotiating networks in oligopoly markets for price sensitive products ( Oral ) > link | naman shukla 🔗 |
-
|
Strategic clustering ( Oral ) > link | Ana-Andreea Stoica · Christos Papadimitriou 🔗 |
-
|
One for One, or All for All: Equilibria and Optimality of Collaboration in Federated Learning ( Oral ) > link | Richard Phillips · Han Shao · Avrim Blum · Nika Haghtalab 🔗 |
-
|
Regret, stability, and fairness in matching markets with bandit learners ( Oral ) > link | Sarah Cen · Devavrat Shah 🔗 |
-
|
On classification of strategic agents who can both game and improve ( Oral ) > link | Saba Ahmadi · Hedyeh Beyhaghi · Avrim Blum · Keziah Naggita 🔗 |
-
|
The Strategic Perceptron ( Oral ) > link | Saba Ahmadi · Hedyeh Beyhaghi · Avrim Blum · Keziah Naggita 🔗 |
-
|
Price Discovery and Efficiency in Waiting Lists: A Connection to Stochastic Gradient Descent ( Oral ) > link | Itai Ashlagi · Jacob Leshno · Pengyu Qian · Amin Saberi 🔗 |
-
|
Unfairness Despite Awareness: Group-Fair Classification with Strategic Agents ( Oral ) > link | Andrew Estornell · Sanmay Das · Yang Liu · Yevgeniy Vorobeychik 🔗 |
-
|
Learning Losses for Strategic Classification ( Oral ) > link | Tosca Lechner · Ruth Urner 🔗 |
-
|
Normative disagreement as a challenge for Cooperative AI ( Oral ) > link | Julian Stastny · Maxime RichĂ© · Aleksandr Lyzhov · Johannes Treutlein · Allan Dafoe · Jesse Clifton 🔗 |
-
|
Learning through Recourse under Censoring ( Oral ) > link | Jennifer Chien · Berk Ustun · Margaret Roberts 🔗 |
-
|
Pessimistic Offline Reinforcement Learning with Multiple Agents ( Oral ) > link | Yihang Chen 🔗 |
-
|
Promoting Resilience of Multi-Agent Reinforcement Learning via Confusion-Based Communication ( Oral ) > link | Ofir Abu · Sarah Keren · Matthias Gerstgrasser · Jeffrey S Rosenschein 🔗 |
-
|
Game Redesign in No-regret Game Playing ( Oral ) > link | Yuzhe Ma · Young Wu · Jerry Zhu 🔗 |
-
|
Pseudo-Competitive Games and Algorithmic Pricing ( Oral ) > link | Chamsi Hssaine · Vijay Kamble · Siddhartha Banerjee 🔗 |
-
|
Learning in Matrix Games can be Arbitrarily Complex ( Oral ) > link | Gabriel Andrade · Rafael Frongillo · Georgios Piliouras 🔗 |
-
|
Test-optional Policies: Overcoming Strategic Behavior and Informational Gaps ( Oral ) > link | Zhi Liu · Nikhil Garg 🔗 |
-
|
Models of fairness in federated learning ( Oral ) > link | Kate Donahue · Jon Kleinberg 🔗 |
-
|
Improving Robustness of Malware Classifiers using Adversarial Strings Generated from Perturbed Latent Representations ( Oral ) > link | Marek Galovic · Branislav Bosansky · Viliam Lisy 🔗 |
-
|
Improving Fairness in Credit Lending Models using Subgroup Threshold Optimization ( Oral ) > link | Cecilia Ying · Stephen Thomas 🔗 |
-
|
The Platform Design Problem ( Oral ) > link | Christos Papadimitriou · Kiran Vodrahalli · Mihalis Yannakakis 🔗 |
-
|
Strategic Classification in the Dark ( Oral ) > link | Ganesh Ghalme · Vineet Nair · Itay Eilat · Inbal Talgam-Cohen · Nir Rosenfeld 🔗 |
-
|
Scoring Rules for Performative Binary Prediction ( Oral ) > link | Alan Chan 🔗 |
-
|
Approximating Bayes Nash Equilibria in Auction Games via Gradient Dynamics ( Oral ) > link | Maximilian Fichtl · Matthias Oberlechner · Martin Bichler 🔗 |
-
|
Strategic Classification Made Practical ( Oral ) > link | Nir Rosenfeld · Sagi Levanon 🔗 |
-
|
Nash Convergence of Mean-Based Learning Algorithms in First Price Auctions ( Oral ) > link | Xiaotie Deng · Xinyan Hu · Tao Lin · Weiqiang Zheng 🔗 |
-
|
Bayesian Persuasion for Algorithmic Recourse ( Oral ) > link | Keegan Harris · Valerie Chen · Joon Kim · Ameet S Talwalkar · Hoda Heidari · Steven Wu 🔗 |
-
|
Reward-Free Attacks in Multi-Agent Reinforcement Learning ( Oral ) > link | Ted Fujimoto · Tim Doster · Adam Attarian · Jill Brandenberger · Nathan Hodas 🔗 |
-
|
Reward Poisoning in Reinforcement Learning: Attacks Against Unknown Learners in Unknown Environments ( Oral ) > link | Amin Rakhsha · Xuezhou Zhang · Jerry Zhu · Adish Singla 🔗 |
-
|
Global Convergence of Multi-Agent Policy Gradient in Markov Potential Games ( Oral ) > link | Stefanos Leonardos · Will Overman · Ioannis Panageas · Georgios Piliouras 🔗 |
-
|
Exploration-Exploitation in Multi-Agent Competition: Convergence with Bounded Rationality ( Oral ) > link | Stefanos Leonardos · Kelly Spendlove · Georgios Piliouras 🔗 |
-
|
Exploration and Incentives in Reinforcement Learning ( Oral ) > link | Max Simchowitz · Aleksandrs Slivkins 🔗 |
-
|
Timing is Money: The Impact of Arrival Order in Beta-Bernoulli Prediction Markets ( Oral ) > link | Blake Martin · Mithun Chakraborty · Sindhu Kutty 🔗 |
-
|
The Price of Incentivizing Exploration: A Characterization via Thompson Sampling and Sample Complexity ( Oral ) > link | Mark Sellke · Aleksandrs Slivkins 🔗 |
-
|
Coopetition Against an Amazon ( Oral ) > link | Ronen Gradwohl · Moshe Tennenholtz 🔗 |