430 citations · 856 across the 28 of their papers we have counts for
12 papers · 1 filter
Out of the Ordinary: Spectrally Adapting Regression for Covariate Shift
Benjamin Eyre, Elliot Creager, David Madras +2
Designing deep neural network classifiers that perform robustly on distributions differing from the available training data is an active area of machine learning research. However,…
When does Privileged Information Explain Away Label Noise?
Guillermo Ortiz-Jimenez, Mark Collier, Anant Nawalgaria +4
Leveraging privileged information (PI), or features available during training but not at test time, has recently been shown to be an effective method for addressing label noise. Ho…
Fairness and robustness in anti-causal prediction
Maggie Makar, Alexander D'Amour
Robustness to distribution shift and fairness have independently emerged as two important desiderata required of modern machine learning models. While these two desiderata seem rel…
Boosting the interpretability of clinical risk scores with intervention predictions
Eric Loreaux, Ke Yu, Jonas Kemp +8
Machine learning systems show significant promise for forecasting patient adverse events via risk scores. However, these risk scores implicitly encode assumptions about future inte…
Diagnosing failures of fairness transfer across distribution shift in real-world medical settings
Jessica Schrouff, Natalie Harris, Oluwasanmi Koyejo +14
Diagnosing and mitigating changes in model fairness under distribution shift is an important component of the safe deployment of machine learning in healthcare settings. Importantl…
Counterfactual Invariance to Spurious Correlations: Why and How to Pass Stress Tests
Victor Veitch, Alexander D'Amour, Steve Yadlowsky +1
Informally, a 'spurious correlation' is the dependence of a model on some aspect of the input data that an analyst thinks shouldn't matter. In machine learning, these have a know-i…
Causally motivated Shortcut Removal Using Auxiliary Labels
Maggie Makar, Ben Packer, Dan Moldovan +3
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-motiv…
Underspecification Presents Challenges for Credibility in Modern Machine Learning
Alexander D'Amour, Katherine Heller, Dan Moldovan +37
ML models often exhibit unexpectedly poor behavior when they are deployed in real-world domains. We identify underspecification as a key reason for these failures. An ML pipeline i…
Evaluating Prediction-Time Batch Normalization for Robustness under Covariate Shift
Zachary Nado, Shreyas Padhy, D. Sculley +3
Covariate shift has been shown to sharply degrade both predictive accuracy and the calibration of uncertainty estimates for deep learning models. This is worrying, because covariat…
A Biologically Plausible Benchmark for Contextual Bandit Algorithms in Precision Oncology Using in vitro Data
Niklas T. Rindtorff, MingYu Lu, Nisarg A. Patel +2
Precision oncology, the genetic sequencing of tumors to identify druggable targets, has emerged as the standard of care in the treatment of many cancers. Nonetheless, due to the pa…
Detecting Underspecification with Local Ensembles
David Madras, James Atwood, Alex D'Amour
We present local ensembles, a method for detecting underspecification -- when many possible predictors are consistent with the training data and model class -- at test time in a pr…
BriarPatches: Pixel-Space Interventions for Inducing Demographic Parity
Alexey A. Gritsenko, Alex D'Amour, James Atwood +2
We introduce the BriarPatch, a pixel-space intervention that obscures sensitive attributes from representations encoded in pre-trained classifiers. The patches encourage internal m…