Rajesh Ranganath

research

∙ 08/24/2023

Don't blame Dataset Shift! Shortcut Learning due to Gradients and Cross Entropy

Common explanations for shortcut learning assume that the shortcut impro...

0 Aahlad Puli, et al. ∙

research

∙ 08/08/2023

When More is Less: Incorporating Additional Datasets Can Hurt Performance By Introducing Spurious Correlations

In machine learning, incorporating more data is often seen as a reliable...

0 Rhys Compton, et al. ∙

research

∙ 03/22/2023

A dynamic risk score for early prediction of cardiogenic shock using machine learning

Myocardial infarction and heart failure are major cardiovascular disease...

0 Yuxuan Hu, et al. ∙

research

∙ 02/24/2023

Don't be fooled: label leakage in explanation methods and the importance of their quantitative evaluation

Feature attribution methods identify which features of an input most inf...

0 Neil Jethani, et al. ∙

research

∙ 02/14/2023

Where to Diffuse, How to Diffuse, and How to Get Back: Automated Learning for Multivariate Diffusions

Diffusion-based generative models (DBGMs) perturb data to a target noise...

0 Raghav Singhal, et al. ∙

research

∙ 02/08/2023

Robustness to Spurious Correlations Improves Semantic Out-of-Distribution Detection

Methods which utilize the outputs or feature representations of predicti...

0 Lily H. Zhang, et al. ∙

research

∙ 01/27/2023

On the Feasibility of Machine Learning Augmented Magnetic Resonance for Point-of-Care Identification of Disease

Early detection of many life-threatening diseases (e.g., prostate and br...

0 Raghav Singhal, et al. ∙

research

∙ 10/04/2022

Nuisances via Negativa: Adjusting for Spurious Correlations via Data Augmentation

There exist features that are related to the label in the same way acros...

0 Aahlad Puli, et al. ∙

research

∙ 09/15/2022

Decision making in cancer: Causal questions require causal answers

Treatment decisions in cancer care are guided by treatment effect estima...

0 Wouter A. C. van Amsterdam, et al. ∙

research

∙ 08/23/2022

Survival Mixture Density Networks

Survival analysis, the art of time-to-event modeling, plays an important...

0 Xintian Han, et al. ∙

research

∙ 08/18/2022

DIET: Conditional independence testing with marginal dependence measures of residual information

Conditional randomization tests (CRTs) assess whether a variable x is pr...

0 Mukund Sudarshan, et al. ∙

research

∙ 06/23/2022

Set Norm and Equivariant Skip Connections: Putting the Deep in Deep Sets

Permutation invariant neural networks are a promising tool for making pr...

0 Lily H. Zhang, et al. ∙

research

∙ 04/29/2022

Conditional average treatment effect estimation with treatment offset models

Treatment effect estimates are often available from randomized controlle...

0 Wouter A. C. van Amsterdam, et al. ∙

research

∙ 12/02/2021

Quantile Filtered Imitation Learning

We introduce quantile filtered imitation learning (QFIL), a novel policy...

0 David Brandfonbrener, et al. ∙

research

∙ 12/01/2021

Learning Invariant Representations with Missing Data

Spurious correlations allow flexible models to predict well during train...

0 Mark Goldstein, et al. ∙

research

∙ 11/16/2021

Inverse-Weighted Survival Games

Deep models trained through maximum likelihood have achieved state-of-th...

0 Xintian Han, et al. ∙

research

∙ 07/15/2021

FastSHAP: Real-Time Shapley Value Estimation

Shapley values are widely used to explain black-box models, but they are...

11 Neil Jethani, et al. ∙

research

∙ 07/14/2021

Understanding Failures in Out-of-Distribution Detection with Deep Generative Models

Deep generative models (DGMs) seem a natural fit for detecting out-of-di...

0 Lily H. Zhang, et al. ∙

research

∙ 06/29/2021

Predictive Modeling in the Presence of Nuisance-Induced Spurious Correlations

Deep predictive models often make use of spurious correlations between t...

0 Aahlad Puli, et al. ∙

research

∙ 06/16/2021

Offline RL Without Off-Policy Evaluation

Most prior approaches to offline reinforcement learning (RL) have taken ...

0 David Brandfonbrener, et al. ∙

research

∙ 03/02/2021

Have We Learned to Explain?: How Interpretability Methods Can Learn to Encode Predictions in their Interpretations

While the need for interpretable machine learning has been established, ...

0 Neil Jethani, et al. ∙

research

∙ 02/17/2021

Causal Estimation with Functional Confounders

Causal inference relies on two fundamental assumptions: ignorability and...

0 Aahlad Puli, et al. ∙

research

∙ 01/13/2021

X-CAL: Explicit Calibration for Survival Analysis

Survival analysis models the distribution of time until an event of inte...

0 Mark Goldstein, et al. ∙

research

∙ 09/23/2020

Probabilistic Machine Learning for Healthcare

Machine learning can be used to make sense of healthcare data. Probabili...

113 Irene Y. Chen, et al. ∙

research

∙ 07/31/2020

Deep Direct Likelihood Knockoffs

Predictive modeling often uses black box machine learning methods, such ...

2 Mukund Sudarshan, et al. ∙

research

∙ 06/27/2020

Overfitting and Optimization in Offline Policy Learning

We consider the task of policy learning from an offline dataset generate...

11 David Brandfonbrener, et al. ∙

research

∙ 01/09/2020

The Counterfactual χ-GAN

Causal inference often relies on the counterfactual framework, which req...

15 Amelia J. Averitt, et al. ∙

research

∙ 10/31/2019

Energy-Inspired Models: Learning with Sampler-Induced Distributions

Energy-based models (EBMs) are powerful probabilistic models, but suffer...

18 Dieterich Lawson, et al. ∙

research

∙ 08/02/2019

Population Predictive Checks

Bayesian modeling has become a staple for researchers analyzing data. Th...

0 Rajesh Ranganath, et al. ∙

research

∙ 07/08/2019

Generalized Control Functions via Variational Decoupling

Causal estimation relies on separating the variation in the outcome due ...

1 Aahlad Manas Puli, et al. ∙

research

∙ 07/02/2019

Reproducibility in Machine Learning for Health

Machine learning algorithms designed to characterize, monitor, and inter...

16 Matthew B. A. McDermott, et al. ∙

research

∙ 05/13/2019

Adversarial Examples for Electrocardiograms

Among all physiological signals, electrocardiogram (ECG) has seen some o...

9 Xintian Han, et al. ∙

research

∙ 04/10/2019

ClinicalBERT: Modeling Clinical Notes and Predicting Hospital Readmission

Clinical notes contain information about patients that goes beyond struc...

0 Kexin Huang, et al. ∙

research

∙ 04/09/2019

Kernelized Complete Conditional Stein Discrepancy

Much of machine learning relies on comparing distributions with discrepa...

18 Raghav Singhal, et al. ∙

research

∙ 03/25/2019

The Random Conditional Distribution for Higher-Order Probabilistic Inference

The need to condition distributional properties such as expectation, var...

0 Zenna Tavares, et al. ∙

research

∙ 03/08/2019

Support and Invertibility in Domain-Invariant Representations

Learning domain-invariant representations has become a popular approach ...

10 Fredrik D. Johansson, et al. ∙

research

∙ 03/07/2019

The Variational Predictive Natural Gradient

Variational inference transforms posterior inference into parametric opt...

4 Da Tang, et al. ∙

research

∙ 01/16/2019

Soft Constraints for Inference with Declarative Knowledge

We develop a likelihood free inference procedure for conditioning a prob...

2 Zenna Tavares, et al. ∙

research

∙ 06/01/2018

Opportunities in Machine Learning for Healthcare

Healthcare is a natural arena for the application of machine learning, e...

0 Marzyeh Ghassemi, et al. ∙

research

∙ 05/21/2018

Multiple Causal Inference with Latent Confounding

Causal inference from observational data requires assumptions. These ass...

0 Rajesh Ranganath, et al. ∙

research

∙ 05/03/2018

Noisin: Unbiased Regularization for Recurrent Neural Networks

Recurrent neural networks (RNNs) are powerful models of sequential data....

0 Adji B. Dieng, et al. ∙

research

∙ 05/31/2017

Variational Sequential Monte Carlo

Variational inference underlies many recent advances in large scale prob...

0 Christian A. Naesseth, et al. ∙

research

∙ 05/24/2017

Proximity Variational Inference

Variational inference is a powerful approach for approximate posterior i...

0 Jaan Altosaar, et al. ∙

research

∙ 02/28/2017

Hierarchical Implicit Models and Likelihood-Free Variational Inference

Implicit probabilistic models are a flexible class of models defined by ...

0 Dustin Tran, et al. ∙

research

∙ 11/01/2016

Variational Inference via χ-Upper Bound Minimization

Variational inference (VI) is widely used as an efficient alternative to...

0 Adji B. Dieng, et al. ∙

research

∙ 10/27/2016

Operator Variational Inference

Variational inference is an umbrella term for algorithms which cast Baye...

0 Rajesh Ranganath, et al. ∙

research

∙ 08/06/2016

Deep Survival Analysis

The electronic health record (EHR) provides an unprecedented opportunity...

0 Rajesh Ranganath, et al. ∙

research

∙ 03/02/2016

Automatic Differentiation Variational Inference

Probabilistic modeling is iterative. A scientist posits a simple model, ...

0 Alp Kucukelbir, et al. ∙

research

∙ 11/20/2015

The Variational Gaussian Process

Variational inference is a powerful tool for approximate inference, and ...

0 Dustin Tran, et al. ∙

research

∙ 11/07/2015

Hierarchical Variational Models

Black box variational inference allows researchers to easily prototype a...

0 Rajesh Ranganath, et al. ∙

Rajesh Ranganath

Featured Co-authors