Author name cluster

Michael Sjoding

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

2 papers

1 author row

NeurIPS Conference 2022 Conference Paper

Learning Concept Credible Models for Mitigating Shortcuts

Jiaxuan Wang
Sarah Jabbour
Maggie Makar
Michael Sjoding
Jenna Wiens

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 robust and accurate models from biased training data. In contrast to previous work, we do not rely solely on known concepts, but allow the model to also learn unknown concepts. We propose two approaches for mitigating shortcuts that incorporate domain knowledge, while accounting for potentially important yet unknown concepts. The first approach is two-staged. After fitting a model using known concepts, it accounts for the residual using unknown concepts. While flexible, we show that this approach is vulnerable when shortcuts are correlated with the unknown concepts. This limitation is addressed by our second approach that extends a recently proposed regularization penalty. Applied to two real-world datasets, we demonstrate that both approaches can successfully mitigate shortcut learning.

PDF Details

NeurIPS Conference 2022 Conference Paper

Leveraging Factored Action Spaces for Efficient Offline Reinforcement Learning in Healthcare

Shengpu Tang
Maggie Makar
Michael Sjoding
Finale Doshi-Velez
Jenna Wiens

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 combinations; this is particularly problematic for offline settings, where data may be limited. In this work, we propose a form of linear Q-function decomposition induced by factored action spaces. We study the theoretical properties of our approach, identifying scenarios where it is guaranteed to lead to zero bias when used to approximate the Q-function. Outside the regimes with theoretical guarantees, we show that our approach can still be useful because it leads to better sample efficiency without necessarily sacrificing policy optimality, allowing us to achieve a better bias-variance trade-off. Across several offline RL problems using simulators and real-world datasets motivated by healthcare, we demonstrate that incorporating factored action spaces into value-based RL can result in better-performing policies. Our approach can help an agent make more accurate inferences within underexplored regions of the state-action space when applying RL to observational datasets.

PDF Details