Speaker: Eden Saig

Title: Delegated Classification

Abstract: What happens when machine learning is outsourced to profit-maximizing agents?

In this work, we propose a theoretical framework for incentive-aware delegation of machine learning tasks. We model delegation as a principal-agent game, in which accurate learning can be incentivized by the principal using performance-based...

Read more about Delegated Classification

Speaker: Yonatan Sompolinsky (Harvard)

Abstract: We tackle the problem of Miners Extracted Value (MEV), where a transaction sequencer extracts profit off users, by frontrunning pending transactions, sandwiching others, or carrying out any other form of ordering manipulations. Most transaction settlement services are designed such that, in each round, a single sequencer is granted full, unrestricted permission to sequence pending transactions. Accordingly, to undermine sequencer monopoly, we devise an auction that forces competition...

Read more about Competitive market design for transaction sequencing

Speaker: Berk Ustun (UCSD)

Title: When Personalization Harms Performance
 

Abstract: Clinical prediction models often encode group attributes like sex, age, and HIV status for personalization – i.e., to assign more accurate predictions to heterogeneous subpopulations. In this talk, I will describe how such practices inadvertently lead to worsenalization, by assigning unnecessarily inaccurate predictions to minority groups. I will discuss how these effects violate our basic expectations from personalization...

Read more about When Personalization Harms Performance

Speaker: John Horton (MIT)

Title: Automated Social Science: A Structural Causal Model-Based Approach

Abstract:

We present an approach for automatically generating and testing, in silico, social scientific...

Read more about Automated Social Science: A Structural Causal Model-Based Approach

Speaker: Zhuoran Yang

Title: Reinforcement Learning Meets Bilevel Optimization: Learning Leader-Follower Games with Sample Efficiency

Abstract: In this talk, I will introduce methods that modify the optimism principle for reinforcement learning in leader-follower games, especially when the follower's reward function is unknown. Such problems generally face statistical challenges due to the ill-posed nature of the best response function. I will discuss two cases that overcome these challenges. The first involves a fully rational follower with a...

Read more about Reinforcement Learning Meets Bilevel Optimization: Learning Leader-Follower Games with Sample Efficiency

1st Speaker:  Shi Feng (Harvard)

Title: Reveal Planning Capability of Autoregressive Learning in Large Language Models

Abstract: Search and planning are fundamental constructs of human intelligence, involved in almost every aspect of our daily lives, from completing tasks at work to organizing trips, to seeking mathematical proofs of theorems, and more. Studying the planning capabilities of large language models (LLMs) can help us understand the differences in the decision-making processes between humans and artificial...

Read more about Reveal Planning Capability of Autoregressive Learning in Large Language Models and Computing Voting Rules with Elicited Incomplete Votes

Speaker: Tomer Ezra (Harvard)

Title: Contract Design in Combinatorial Settings

Abstract: We study two combinatorial settings of the contract design problem, in which a principal wants to delegate the execution of a costly task. In the first setting, the principal delegates the task to an agent that can take any subset of a given set of unobservable actions, each of which has an associated cost. The principal receives a reward which is a combinatorial function of the actions taken by the agent. In the second setting, we study the single-principal multi-...

Read more about Contract Design in Combinatorial Settings

Speaker: Martin Bichler

Abstract: Equilibrium problems in Bayesian auction games can be described as systems of differential equations. Depending on the model assumptions, these equations might be such that we do not have an exact mathematical solution theory. The lack of analytical or numerical techniques with guaranteed convergence for the equilibrium problem has plagued the field and limited equilibrium analysis to rather simple auction models such as single-object auctions. Recent progress in equilibrium learning led to algorithms that find approximate...

Read more about Learning Bayes-Nash Equilibria in Auctions and Contests

Speaker: Brian Zhang (CMU)

Title: Computing Optimal Equilibria and Mechanisms via Learning in Zero-Sum Extensive-Form Games

Abstract: We introduce a unified framework for understanding optimal equilibria in general games by explicitly augmenting the game with a mediator who can communicate with players. By varying restrictions governing the communication, the framework covers a wide family of solution concepts and problems including---but not limited to---communication...

Read more about Computing Optimal Equilibria and Mechanisms via Learning in Zero-Sum Extensive-Form Games

Speaker: Yichi Zhang (University of Michigan)

Talk Title: Eliciting Honest Information From Authors Using Sequential Review
Abstract: In the setting of conference peer review, the conference aims to accept high-quality papers and reject low-quality papers based on noisy review scores. A recent work proposes the isotonic mechanism, which can elicit the ranking of paper qualities from an author with multiple submissions to help improve the conference’s decisions. However, the isotonic mechanism relies on the assumption that the author’s...

Read more about Eliciting Honest Information From Authors Using Sequential Review

Speaker: Nir Rosenfeld (Technion)

Title: Strategic Classification: Learning With Data That 'Behaves'

Abstract: The growing success of machine learning across a wide range of domains and applications has made it appealing to be used also as a tool for informing decisions about humans. But humans are not your conventional input: they have goals, beliefs, and aspirations, and take action to promote their own self-interests. Given that standard learning methods are not designed to handle inputs that "behave", it is natural to ask: how should we...

Read more about Strategic Classification: Learning With Data That 'Behaves'

1st Speaker: Sara Fish (Harvard)

 

Title: Algorithmic Collusion by Large Language Models

Abstract: The rise of algorithmic pricing raises concerns that algorithms might collude to maximize firm profits, to the detriment of consumers. We conduct experiments with algorithmic pricing agents based on Large Language Models (LLMs), and specifically on OpenAI's GPT-4. We find that (1) LLM-based pricing...

Read more about Algorithmic Collusion by Large Language Models & Equilibrium of Data Markets with Externality

...

Read more about Towards Behavior-Informed Machine Learning

Speaker: Yuqing Kong (Peking University)

Title: Eliciting Information without Verification from Humans and Machines

Abstract: Many application domains rely on eliciting high-quality (subjective) information. This presentation will talk about how to elicit and aggregate information from both human and machine participants, especially when the information cannot be directly verified. The first part of the talk presents a mechanism, DMI-...

Read more about Eliciting Information without Verification from Humans and Machines

Speaker: Stefano V. Albrecht (University of Edinburgh)

Title: Deep Reinforcement Learning for Multi-Agent Interaction

Abstract: Our group specialises in developing machine learning algorithms for autonomous systems control, with a particular focus on deep reinforcement learning and multi-agent reinforcement learning. We have a focus on problems of optimal decision making, prediction, and coordination in multi-agent systems. In this talk, I will give an overview of our research agenda along with some recent published papers in these areas, including... Read more about Deep Reinforcement Learning for Multi-Agent Interaction