2024 Apr 18

Delegated Classification

1:30pm to 2:30pm

Location:

SEC 3.301+3.302

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...

2024 Apr 16

Competitive market design for transaction sequencing

1:00pm to 2:00pm

Location:

SEC 4.307

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...

2024 Apr 12

Automated Social Science: A Structural Causal Model-Based Approach

1:30pm to 2:30pm

Location:

SEC 1.413

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...

2024 Apr 05

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

1:30pm to 2:30pm

Location:

SEC 1.413

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...

2024 Mar 29

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

1:30pm to 2:30pm

Location:

SEC 1.413

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...

2024 Mar 22

Contract Design in Combinatorial Settings

1:30pm to 2:30pm

Location:

SEC 1.413

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-...

2024 Mar 07

Learning Bayes-Nash Equilibria in Auctions and Contests

1:30pm to 2:30pm

Location:

SEC 3.303 (third floor)

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...

2024 Mar 04

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

1:30pm to 2:30pm

Location:

SEC 2.122 + 2.123 (second floor).

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...

2024 Feb 29

Strategic Classification: Learning With Data That 'Behaves'

1:30pm to 2:30pm

Location:

SEC 3.301+3.302

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...

2024 Feb 23

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

1:30pm to 2:30pm

Location:

SEC 1.413

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...

2024 Feb 16

Towards Behavior-Informed Machine Learning

1:30pm to 2:30pm

Location:

SEC 1.413

...

2024 Feb 09

Eliciting Information without Verification from Humans and Machines

1:30pm to 2:30pm

Location:

SEC 1.413

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-...

2024 Jan 26

Eliciting Honest Information From Authors Using Sequential Review

1:30pm to 2:30pm

Location:

SEC 1.413

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...

2023 Dec 08

Deep Reinforcement Learning for Multi-Agent Interaction

1:30pm to 2:30pm

Location:

SEC 1.413

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

2023 Nov 10

Game-Theoretic Reinforcement Learning

1:30pm to 2:30pm

Location:

SEC 1.413

Speaker: Stephen McAleer (CMU postdoc)

Title: Game-Theoretic Reinforcement Learning

Abstract: Game-theoretic reinforcement learning studies reinforcement learning algorithms that have guarantees of convergence to equilibrium. In this talk I give an overview of game-theoretic reinforcement learning, categorizing it into three main classes: double oracle-based methods, counterfactual regret minimization-based methods, and policy-gradient-based methods. I then introduce state-of-the-art approaches within each algorithmic class, and show how these...

2023 Nov 03

Fine-tuning Games

1:30pm to 2:30pm

Location:

SEC 1.413

Speaker: Benjamin Laufer (Cornell Tech)

Talk Title: Fine-tuning Games

Abstract: Major advances in Machine Learning (ML) and Artificial Intelligence (AI) increasingly take the form of developing and releasing general-purpose...

Incentive-theoretic Hypothesis Testing

1:30pm to 2:30pm

Location:

SEC 1.413

Speaker: Stephen Bates (MIT)

Title: Incentive-theoretic Hypothesis Testing

Abstract: Contemporary scientific research is a distributed, collaborative endeavor, carried out by teams of researchers, regulatory institutions, funding agencies, commercial partners, and scientific bodies, all interacting with each other and facing different incentives. To maintain scientific rigor, statistical methods should acknowledge this state of affairs. To this end, we study hypothesis testing when there is an...

2023 Oct 26

Iterative Network Pricing for Ridesharing Platforms

11:00am to 12:00pm

Location:

SEC 3.301+3.302

Speaker: Hongyao Ma (Columbia Business School)

Time & location: 11:00 - 12:00 on Thursday, Oct 26, at

Title: Iterative Network Pricing for Ridesharing Platforms

Abstract: Ridesharing platforms match riders and drivers, using dynamic pricing to balance supply and demand. The origin-based “surge pricing”, however, does not depend on the market condition of trip destinations, leading to inefficient trip flows in space and incentivizes drivers to strategize. In this work, we introduce the Iterative Network...

2023 Oct 20

Fair Price Discrimination

1:30pm to 2:30pm

Location:

SEC 1.413

Speaker: Kangning Wang (stanford postdoc)

Title: Fair Price Discrimination

Abstract: A seller is pricing identical copies of a good to a stream of unit-demand buyers. Each buyer has a value on the good as his private information. The seller only knows the empirical value distribution of the buyer population and chooses the revenue-optimal price. We consider a widely studied third-degree price discrimination model where an information intermediary with perfect knowledge of the arriving buyer'...

2023 Oct 13

Ex-Post Group Fairness and Individual Fairness in Ranking

1:30pm to 2:30pm

Location:

SEC 1.413

Speaker: Sruthi Gorantla (IISc Bangalore)

Title: Ex-Post Group Fairness and Individual Fairness in Ranking

Abstract: Fair ranking tasks, which ask to rank a set of items to maximize utility subject to satisfying group-fairness constraints, have gained significant interest in algorithmic fairness, information retrieval, and machine learning literature. Recent works identify uncertainty in the utilities of items as a primary cause of unfairness and propose randomized rankings that achieve ex-ante fairer exposure and better robustness than...

2023 Sep 22

The Value of Individual Risk Prediction in Wisconsin Public Schools

1:30pm to 3:00pm

Location:

SEC 1.413

The EconCS Group holds an Economics & Computer Science research seminar each semester. Fall '23 meetings are at 1:30 - 2:30 PM on Fridays in SEC 1.413. Seminar Coordinators are Shirley Zhang and Tao Lin. SEC 1.413 is on ground level at the NW corner of SEC, which is open to the public. The seminar is in-person only. Speaker: Juan Perdomo (Harvard CRCS postdoc)

...

2023 Apr 21

Marketplace Experimentation and Interference Effects

1:00pm to 2:00pm

Location:

SEC 1.413, & streamed via Zoom at: https://harvard.zoom.us/j/95184948637?pwd=bXBIc2U5MEZ0QmRUb01WQ0o0SXRCdz09

This Friday, 1-2pm in SEC 1.413, Hannah Li will be speaking in person on:

Marketplace Experimentation and Interference Effects

Abstract:

Platforms often rely on experiments (A/B tests) to aid decision-making. However, in many marketplace experiments, interactions between users can create interference effects that lead to biased estimates. We develop mathematical models to capture these interference effects and study the biases that arise. In particular, we are able to highlight and formalize the relationship...

2023 Apr 14

A Simple Theory of Vampire Attacks

1:00pm to 2:00pm

Location:

Zoom at the link: https://harvard.zoom.us/j/95184948637?pwd=bXBIc2U5MEZ0QmRUb01WQ0o0SXRCdz09

Scott Kominers (Harvard Business School)

A Simple Theory of Vampire Attacks

Abstract:

Firms often find it valuable to lock in repeat consumers, and they often do so via loyalty programs such as frequent-flyer miles or discounts for returning consumers. We introduce a model of loyalty programs in the presence of competition and show that, surprisingly, such programs result in higher prices for all consumers in equilibrium.

However, competitors may also find it valuable to identify repeat consumers of other firms and convince them to...

2023 Apr 07

Included-variable bias and everything but the kitchen sink

1:00pm to 2:00pm

Location:

SEC 1.413, & streamed via Zoom at: https://harvard.zoom.us/j/95184948637?pwd=bXBIc2U5MEZ0QmRUb01WQ0o0SXRCdz09

This Friday, 1-2pm in SEC 1.413, we are very excited to have Sharad Goel (Harvard Kennedy School) speak in-person on:

Included-variable bias and everything but the kitchen sink

Abstract: When estimating the risk of an adverse outcome, common statistical guidance is to include all available factors to maximize predictive performance. Similarly, in observational studies of discrimination, general practice is to adjust for all potential confounds to... Read more about Included-variable bias and everything but the kitchen sink

2023 Mar 31

Group fairness in dynamic refugee assignment

1:00pm to 2:00pm

Location:

SEC 1.413, & streamed via Zoom at: https://harvard.zoom.us/j/95184948637?pwd=bXBIc2U5MEZ0QmRUb01WQ0o0SXRCdz09

This Friday, 1-2pm in SEC 1.413, we will have professor Thodoris Lykouris from MIT to speak in-person on

Title: Group fairness in dynamic refugee assignment

Abstract: ...

2023 Mar 24

Outcome-Driven Dynamic Refugee Assignment with Allocation Balancing

1:00pm to 2:00pm

Location:

SEC 1.413, & streamed via Zoom at: https://harvard.zoom.us/j/95184948637?pwd=bXBIc2U5MEZ0QmRUb01WQ0o0SXRCdz09

Elisabeth C. Paulson (Harvard Business School)

Outcome-Driven Dynamic Refugee Assignment with Allocation Balancing

Abstract: This work proposes two new dynamic assignment algorithms to match refugees and asylum seekers to geographic localities within a host country. The first, currently implemented in a multi-year pilot in Switzerland, seeks to maximize the average predicted employment level (or any measured outcome of interest) of refugees through a minimum-discord online assignment algorithm. Although the proposed algorithm achieves near-optimal expected...

2023 Mar 10

Multi-channel Autobidding with Budget and ROI Constraints

1:00pm to 2:00pm

Location:

SEC 1.413, & streamed via Zoom at: https://harvard.zoom.us/j/95184948637?pwd=bXBIc2U5MEZ0QmRUb01WQ0o0SXRCdz09

Negin Golrezaei, MIT Sloan

March 10, 2023, SEC 1.413 (in-person)

Multi-channel Autobidding with Budget and ROI Constraints

Abstract: In digital online advertising, advertisers procure ad impressions simultaneously on multiple platforms, or so-called channels, such as Google Ads, Meta Ads Manager, etc., each of which consists of numerous ad auctions. We study how an advertiser maximizes total conversion (e.g. ad clicks) while satisfying aggregate return-on-investment (ROI) and budget constraints across all channels. In practice, an advertiser does...

2023 Mar 03

Tao Lin & Lily Xu talks

1:00pm to 2:00pm

Location:

SEC 1.413, & streamed via Zoom at: https://harvard.zoom.us/j/95184948637?pwd=bXBIc2U5MEZ0QmRUb01WQ0o0SXRCdz09

Tao Lin

Persuading a Behavioral Agent: Approximately Best Responding and Learning

Abstract: The classic Bayesian persuasion model assumes that the receiver is fully Bayesian and best responds to the sender’s signaling scheme. In this talk, I will talk about two alternative (and more realistic) behavioral models for the receiver: (1) approximately best responding, and (2) learning. We analyze how these two behavioral models affect the sender’s utility in the Bayesian persuasion problem. We first show that, under natural assumptions, approximately best-...

Auctions between Regret-Minimizing Agents: On Learning Dynamics and User Incentives

1:00pm

Location:

The Zoom link is as usual: https://harvard.zoom.us/j/95184948637?pwd=bXBIc2U5MEZ0QmRUb01WQ0o0SXRCdz09 (password: econcs)

This Friday 1-2pm fully on Zoom, we have Yoav Kolumbus (The Hebrew University of Jerusalem) on:

Auctions between Regret-Minimizing Agents: On Learning Dynamics and User Incentives

Abstract: The usage of automated learning agents is becoming increasingly prevalent in many online economic applications such as online auctions and automated trading. In this talk we will discuss the strategic situations that the users of such automated learning agents are facing. We propose to view the outcomes of the agents’ dynamics as inducing a “meta-game” between the users.... Read more about Auctions between Regret-Minimizing Agents: On Learning Dynamics and User Incentives

2023 Feb 17

The Method of Equal Shares for Participatory Budgeting

1:00pm to 2:00pm

Location:

SEC 1.413, and streamed via Zoom: https://harvard.zoom.us/j/95184948637?pwd=bXBIc2U5MEZ0QmRUb01WQ0o0SXRCdz09

This Friday, 1-2pm in SEC 1.413, we are very excited to have Dominik Peters (LAMSADE) speak in-person on:

The Method of Equal Shares for Participatory Budgeting

Abstract: In Participatory Budgeting, cities allow their residents to influence the...

Fall 2021

Location:

Location:

Location:

Location:

Location:

Seminar history

Location:

Location:

Location:

Location:

Location:

Location:

Location:

Location:

Location:

Location:

Location:

Location:

Location:

Location:

Location:

Location:

Location:

Location:

Location:

Location:

Location:

Location:

Location:

Location:

Location:

Location:

Location:

Location:

Location:

Location:

Filter By