31 citations · 71 across the 22 of their papers we have counts for
23 papers
How I learned to stop worrying and love StopGrads: Stationarity, Convergence, and a case study on Flow Map Learning
Max W. Shen, Mark Goldstein, Zichu Wang +2
Stopgrads are widely used in training machine learning models, but stopgrads can alter the gradient, stationary points and convergence guarantees of the original objective, which c…
Flow Map Learning via Nongradient Vector Flow
Mark Goldstein, Anshuk Uppal, Raghav Singhal +2
Diffusion and flow-based models benefit from simple regression losses, but inference incurs significant overhead because sampling requires integration. Consistency models address t…
Let the Experts Speak: Improving Survival Prediction & Calibration via Mixture-of-Experts Heads
Todd Morrill, Aahlad Puli, Murad Megjhani +2
Deep mixture-of-experts models have attracted a lot of attention for survival analysis problems, particularly for their ability to cluster similar patients together. In practice, g…
Controllably Efficient Language Models
Jatin Prakash, Aahlad Puli, Rajesh Ranganath
The substantial inference costs of attention in transformers motivated the development of efficient sequence mixers: namely sparse and sliding window attention, convolutions and li…
Black Box Causal Inference: Effect Estimation via Meta Prediction
Lucius E. J. Bynum, Aahlad Manas Puli, Diego Herrero-Quevedo +4
Causal inference and the estimation of causal effects plays a central role in decision-making across many areas, including healthcare and economics. Estimating causal effects typic…
Explanations that reveal all through the definition of encoding
Aahlad Puli, Nhi Nguyen, Rajesh Ranganath
Feature attributions attempt to highlight what inputs drive predictive power. Good attributions or explanations are thus those that produce inputs that retain this predictive power…
Contrasting with Symile: Simple Model-Agnostic Representation Learning for Unlimited Modalities
Adriel Saporta, Aahlad Puli, Mark Goldstein +1
Contrastive learning methods, such as CLIP, leverage naturally paired data-for example, images and their corresponding text captions-to learn general representations that transfer…
Robust Anomaly Detection for Particle Physics Using Multi-Background Representation Learning
Abhijith Gandrakota, Lily Zhang, Aahlad Puli +4
Anomaly, or out-of-distribution, detection is a promising tool for aiding discoveries of new particles or processes in particle physics. In this work, we identify and address two o…
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…
When More is Less: Incorporating Additional Datasets Can Hurt Performance By Introducing Spurious Correlations
Rhys Compton, Lily Zhang, Aahlad Puli +1
In machine learning, incorporating more data is often seen as a reliable strategy for improving model performance; this work challenges that notion by demonstrating that the additi…
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…
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…
DIET: Conditional independence testing with marginal dependence measures of residual information
Mukund Sudarshan, Aahlad Manas Puli, Wesley Tansey +1
Conditional randomization tests (CRTs) assess whether a variable is predictive of another variable , having observed covariates . CRTs require fitting a large number of p…
Bayesian Modeling of Marketing Attribution
Ritwik Sinha, David Arbour, Aahlad Manas Puli
In a multi-channel marketing world, the purchase decision journey encounters many interactions (e.g., email, mobile notifications, display advertising, social media, and so on). Th…
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…
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…
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…
Causal Estimation with Functional Confounders
Aahlad Puli, Adler J. Perotte, Rajesh Ranganath
Causal inference relies on two fundamental assumptions: ignorability and positivity. We study causal inference when the true confounder value can be expressed as a function of the…
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…
General Control Functions for Causal Effect Estimation from Instrumental Variables
Aahlad Manas Puli, Rajesh Ranganath
Causal effect estimation relies on separating the variation in the outcome into parts due to the treatment and due to the confounders. To achieve this separation, practitioners oft…
Removing Hidden Confounding by Experimental Grounding
Nathan Kallus, Aahlad Manas Puli, Uri Shalit
Observational data is increasingly used as a means for making individual-level causal predictions and intervention recommendations. The foremost challenge of causal inference from…