AIConfPaper
← Search

Maggie Makar

12 accepted papers

2025

Disentangling misreporting from genuine adaptation in strategic settings: a causal approach

Dylan Zapzalka, Trenton Chang, Lindsay Warrenburg, Sae-Hwan Park, Daniel K Shenfeld, Ravi B Parikh +2
NeurIPS 2025poster

In settings where ML models are used to inform the allocation of resources, agents affected by the allocation decisions might have an incentive to strategically change their features to secure better outcomes. While prior work has studied strategic responses broadly, disentangling misreporting from…

Cited by 0Source ↗Scholar ↗
2024

Hypothesis Testing the Circuit Hypothesis in LLMs

Claudia Shi, Nicolas Beltran-Velez, Achille Nazaret, Carolina Zheng, Adrià Garriga-Alonso, Andrew Jesson +2
NeurIPS 2024poster

Large language models (LLMs) demonstrate surprising capabilities, but we do not understand how they are implemented. One hypothesis suggests that these capabilities are primarily executed by small subnetworks within the LLM, known as circuits. But how can we evaluate this hypothesis? In this paper,…

Cited by 8Source ↗PDF ↗code ↗Scholar ↗
2024

Learning to Rank for Optimal Treatment Allocation Under Resource Constraints

Fahad Kamran, Maggie Makar, Jenna Wiens
AISTATS 2024poster

Current causal inference approaches for estimating conditional average treatment effects (CATEs) often prioritize accuracy. However, in resource constrained settings, decision makers may only need a ranking of individuals based on their estimated CATE. In these scenarios, exact CATE estimation may b…

Cited by 2Source ↗PDF ↗Scholar ↗
2024

Offline Policy Evaluation and Optimization Under Confounding

Chinmaya Kausik, Yangyi Lu, Kevin Tan, Maggie Makar, Yixin Wang, Ambuj Tewari
AISTATS 2024poster

Evaluating and optimizing policies in the presence of unobserved confounders is a problem of growing interest in offline reinforcement learning. Using conventional methods for offline RL in the presence of confounding can not only lead to poor decisions and poor policies, but also have disastrous ef…

Cited by 12Source ↗PDF ↗code ↗Scholar ↗
2024

Who’s Gaming the System? A Causally-Motivated Approach for Detecting Strategic Adaptation

Trenton Chang, Lindsay Warrenburg, Sae-Hwan Park, Ravi B Parikh, Maggie Makar, Jenna Wiens
NeurIPS 2024poster

In many settings, machine learning models may be used to inform decisions that impact individuals or entities who interact with the model. Such entities, or *agents,* may *game* model decisions by manipulating their inputs to the model to obtain better outcomes and maximize some utility. We consider…

Cited by 2Source ↗PDF ↗code ↗Scholar ↗
2022

Causally motivated shortcut removal using auxiliary labels

Maggie Makar, Ben Packer, Dan Moldovan, Davis Blalock, Yoni Halpern, Alexander D’Amour
AISTATS 2022poster

Shortcut learning, in which models make use of easy-to-represent but unstable associations, is a major failure mode for robust machine learning. We study a flexible, causally-motivated approach to training robust predictors by discouraging the use of specific shortcuts, focusing on a common setting…

Cited by 85Source ↗PDF ↗code ↗Scholar ↗
2022

Learning Concept Credible Models for Mitigating Shortcuts

Jiaxuan Wang, Sarah Jabbour, Maggie Makar, Michael Sjoding, Jenna Wiens
NeurIPS 2022accept

During training, models can exploit spurious correlations as shortcuts, resulting in poor generalization performance when shortcuts do not persist. In this work, assuming access to a representation based on domain knowledge (i.e., known concepts) that is invariant to shortcuts, we aim to learn robus…

Cited by 7Source ↗PDF ↗Scholar ↗
2022

Leveraging Factored Action Spaces for Efficient Offline Reinforcement Learning in Healthcare

Shengpu Tang, Maggie Makar, Michael Sjoding, Finale Doshi-Velez, Jenna Wiens
NeurIPS 2022accept

Many reinforcement learning (RL) applications have combinatorial action spaces, where each action is a composition of sub-actions. A standard RL approach ignores this inherent factorization structure, resulting in a potential failure to make meaningful inferences about rarely observed sub-action com…

Cited by 46Source ↗PDF ↗code ↗Scholar ↗
2021

Exploiting structured data for learning contagious diseases under incomplete testing

Maggie Makar, Lauren West, David Hooper, Eric Horvitz, Erica Shenoy, John Guttag
ICML 2021spotlight

One of the ways that machine learning algorithms can help control the spread of an infectious disease is by building models that predict who is likely to become infected making them good candidates for preemptive interventions. In this work we ask: can we build reliable infection prediction models w…

Cited by 0Source ↗PDF ↗code ↗Scholar ↗
2020

Estimation of Bounds on Potential Outcomes For Decision Making

Maggie Makar, Fredrik Johansson, John Guttag, David Sontag
ICML 2020poster

Estimation of individual treatment effects is commonly used as the basis for contextual decision making in fields such as healthcare, education, and economics. However, it is often sufficient for the decision maker to have estimates of upper and lower bounds on the potential outcomes of decision alt…

Cited by 14Source ↗PDF ↗code ↗Scholar ↗