618 citations · 1.9k across the 59 of their papers we have counts for
28 papers · 1 filter
Don't blame Dataset Shift! Shortcut Learning due to Gradients and Cross Entropy
Aahlad Puli, Lily Zhang, Yoav Wald +1
Common explanations for shortcut learning assume that the shortcut improves prediction under the training distribution but not in the test distribution. Thus, models trained via th…
An Effective Meaningful Way to Evaluate Survival Models
Shi-ang Qi, Neeraj Kumar, Mahtab Farrokh +5
One straightforward metric to evaluate a survival prediction model is based on the Mean Absolute Error (MAE) -- the average of the absolute difference between the time predicted by…
A dynamic risk score for early prediction of cardiogenic shock using machine learning
Yuxuan Hu, Albert Lui, Mark Goldstein +18
Myocardial infarction and heart failure are major cardiovascular diseases that affect millions of people in the US. The morbidity and mortality are highest among patients who devel…
Where to Diffuse, How to Diffuse, and How to Get Back: Automated Learning for Multivariate Diffusions
Raghav Singhal, Mark Goldstein, Rajesh Ranganath
Diffusion-based generative models (DBGMs) perturb data to a target noise distribution and reverse this process to generate samples. The choice of noising process, or inference diff…
Don't be fooled: label leakage in explanation methods and the importance of their quantitative evaluation
Neil Jethani, Adriel Saporta, Rajesh Ranganath
Feature attribution methods identify which features of an input most influence a model's output. Most widely-used feature attribution methods (such as SHAP, LIME, and Grad-CAM) are…
Robustness to Spurious Correlations Improves Semantic Out-of-Distribution Detection
Lily H. Zhang, Rajesh Ranganath
Methods which utilize the outputs or feature representations of predictive models have emerged as promising approaches for out-of-distribution (OOD) detection of image inputs. Howe…
On the Feasibility of Machine Learning Augmented Magnetic Resonance for Point-of-Care Identification of Disease
Raghav Singhal, Mukund Sudarshan, Anish Mahishi +7
Early detection of many life-threatening diseases (e.g., prostate and breast cancer) within at-risk population can improve clinical outcomes and reduce cost of care. While numerous…
Beyond Distribution Shift: Spurious Features Through the Lens of Training Dynamics
Nihal Murali, Aahlad Puli, Ke Yu +2
Deep Neural Networks (DNNs) are prone to learning spurious features that correlate with the label during training but are irrelevant to the learning problem. This hurts model gener…
Nuisances via Negativa: Adjusting for Spurious Correlations via Data Augmentation
Aahlad Puli, Nitish Joshi, Yoav Wald +2
In prediction tasks, there exist features that are related to the label in the same way across different settings for that task; these are semantic features or semantics. Features…
From algorithms to action: improving patient care requires causality
Wouter A. C. van Amsterdam, Pim A. de Jong, Joost J. C. Verhoeff +2
In cancer research there is much interest in building and validating outcome predicting outcomes to support treatment decisions. However, because most outcome prediction models are…
Survival Mixture Density Networks
Xintian Han, Mark Goldstein, Rajesh Ranganath
Survival analysis, the art of time-to-event modeling, plays an important role in clinical treatment decisions. Recently, continuous time models built from neural ODEs have been pro…
Set Norm and Equivariant Skip Connections: Putting the Deep in Deep Sets
Lily H. Zhang, Veronica Tozzo, John M. Higgins +1
Permutation invariant neural networks are a promising tool for making predictions from sets. However, we show that existing permutation invariant architectures, Deep Sets and Set T…
New-Onset Diabetes Assessment Using Artificial Intelligence-Enhanced Electrocardiography
Hao Zhang, Neil Jethani, Aahlad Puli +4
Diabetes has a long asymptomatic period which can often remain undiagnosed for multiple years. In this study, we trained a deep learning model to detect new-onset diabetes using 12…
Quantile Filtered Imitation Learning
David Brandfonbrener, William F. Whitney, Rajesh Ranganath +1
We introduce quantile filtered imitation learning (QFIL), a novel policy improvement operator designed for offline reinforcement learning. QFIL performs policy improvement by runni…
Learning Invariant Representations with Missing Data
Mark Goldstein, Jörn-Henrik Jacobsen, Olina Chau +4
Spurious correlations allow flexible models to predict well during training but poorly on related test distributions. Recent work has shown that models that satisfy particular inde…
Inverse-Weighted Survival Games
Xintian Han, Mark Goldstein, Aahlad Puli +3
Deep models trained through maximum likelihood have achieved state-of-the-art results for survival analysis. Despite this training scheme, practitioners evaluate models under other…
Understanding Failures in Out-of-Distribution Detection with Deep Generative Models
Lily H. Zhang, Mark Goldstein, Rajesh Ranganath
Deep generative models (DGMs) seem a natural fit for detecting out-of-distribution (OOD) inputs, but such models have been shown to assign higher probabilities or densities to OOD…
Out-of-distribution Generalization in the Presence of Nuisance-Induced Spurious Correlations
Aahlad Puli, Lily H. Zhang, Eric K. Oermann +1
In many prediction problems, spurious correlations are induced by a changing relationship between the label and a nuisance variable that is also correlated with the covariates. For…
Offline RL Without Off-Policy Evaluation
David Brandfonbrener, William F. Whitney, Rajesh Ranganath +1
Most prior approaches to offline reinforcement learning (RL) have taken an iterative actor-critic approach involving off-policy evaluation. In this paper we show that simply doing…
X-CAL: Explicit Calibration for Survival Analysis
Mark Goldstein, Xintian Han, Aahlad Puli +2
Survival analysis models the distribution of time until an event of interest, such as discharge from the hospital or admission to the ICU. When a model's predicted number of events…
Offline Contextual Bandits with Overparameterized Models
David Brandfonbrener, William F. Whitney, Rajesh Ranganath +1
Recent results in supervised learning suggest that while overparameterized models have the capacity to overfit, they in fact generalize quite well. We ask whether the same phenomen…
The Counterfactual -GAN
Amelia J. Averitt, Natnicha Vanitchanant, Rajesh Ranganath +1
Causal inference often relies on the counterfactual framework, which requires that treatment assignment is independent of the outcome, known as strong ignorability. Approaches to e…
Energy-Inspired Models: Learning with Sampler-Induced Distributions
Dieterich Lawson, George Tucker, Bo Dai +1
Energy-based models (EBMs) are powerful probabilistic models, but suffer from intractable sampling and density evaluation due to the partition function. As a result, inference in E…
Reproducibility in Machine Learning for Health
Matthew B. A. McDermott, Shirly Wang, Nikki Marinsek +3
Machine learning algorithms designed to characterize, monitor, and intervene on human health (ML4H) are expected to perform safely and reliably when operating at scale, potentially…