Search Results for author: Rajesh Ranganath

Found 68 papers, 24 papers with code

Stochastic interpolants with data-dependent couplings

no code implementations5 Oct 2023 Michael S. Albergo, Mark Goldstein, Nicholas M. Boffi, Rajesh Ranganath, Eric Vanden-Eijnden

Generative models inspired by dynamical transport of measure -- such as flows and diffusions -- construct a continuous-time map between two probability densities.


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

no code implementations24 Aug 2023 Aahlad Puli, Lily Zhang, Yoav Wald, Rajesh Ranganath

However, even when the stable feature determines the label in the training distribution and the shortcut does not provide any additional information, like in perception tasks, default-ERM still exhibits shortcut learning.

Inductive Bias

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

1 code implementation8 Aug 2023 Rhys Compton, Lily Zhang, Aahlad Puli, Rajesh Ranganath

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 addition of external datasets in many cases can hurt the resulting model's performance.

An Effective Meaningful Way to Evaluate Survival Models

1 code implementation1 Jun 2023 Shi-ang Qi, Neeraj Kumar, Mahtab Farrokh, Weijie Sun, Li-Hao Kuan, Rajesh Ranganath, Ricardo Henao, Russell Greiner

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 the model and the true event time, over all subjects.

Survival Prediction

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

no code implementations22 Mar 2023 Yuxuan Hu, Albert Lui, Mark Goldstein, Mukund Sudarshan, Andrea Tinsay, Cindy Tsui, Samuel Maidman, John Medamana, Neil Jethani, Aahlad Puli, Vuthy Nguy, Yindalon Aphinyanaphongs, Nicholas Kiefer, Nathaniel Smilowitz, James Horowitz, Tania Ahuja, Glenn I Fishman, Judith Hochman, Stuart Katz, Samuel Bernard, Rajesh Ranganath

We developed a deep learning-based risk stratification tool, called CShock, for patients admitted into the cardiac ICU with acute decompensated heart failure and/or myocardial infarction to predict onset of cardiogenic shock.

Beyond Distribution Shift: Spurious Features Through the Lens of Training Dynamics

1 code implementation18 Feb 2023 Nihal Murali, Aahlad Puli, Ke Yu, Rajesh Ranganath, Kayhan Batmanghelich

(3) We empirically show that the harmful spurious features can be detected by observing the learning dynamics of the DNN's early layers.

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

no code implementations14 Feb 2023 Raghav Singhal, Mark Goldstein, Rajesh Ranganath

For example, extending the inference process with auxiliary variables leads to improved sample quality.

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

no code implementations8 Feb 2023 Lily H. Zhang, Rajesh Ranganath

The detection of shared-nuisance out-of-distribution (SN-OOD) inputs is particularly relevant in real-world applications, as anomalies and in-distribution inputs tend to be captured in the same settings during deployment.

Domain Generalization Out-of-Distribution Detection +1

Nuisances via Negativa: Adjusting for Spurious Correlations via Data Augmentation

no code implementations4 Oct 2022 Aahlad Puli, Nitish Joshi, He He, Rajesh Ranganath

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.

Data Augmentation Natural Language Inference

Decision making in cancer: Causal questions require causal answers

no code implementations15 Sep 2022 Wouter A. C. van Amsterdam, Pim A. de Jong, Joost J. C. Verhoeff, Tim Leiner, Rajesh Ranganath

Recognizing the importance of reliable predictions, the AJCC published a checklist for OPMs to ensure dependable OPM prediction accuracy in the patient population for which the OPM was designed.

Decision Making

Survival Mixture Density Networks

1 code implementation23 Aug 2022 Xintian Han, Mark Goldstein, Rajesh Ranganath

Survival MDN applies an invertible positive function to the output of Mixture Density Networks (MDNs).

Survival Analysis

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

no code implementations18 Aug 2022 Mukund Sudarshan, Aahlad Manas Puli, Wesley Tansey, Rajesh Ranganath

DIET tests the marginal independence of two random variables: $F(x \mid z)$ and $F(y \mid z)$ where $F(\cdot \mid z)$ is a conditional cumulative distribution function (CDF).

Test valid

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

1 code implementation23 Jun 2022 Lily H. Zhang, Veronica Tozzo, John M. Higgins, Rajesh Ranganath

However, we show that existing permutation invariant architectures, Deep Sets and Set Transformer, can suffer from vanishing or exploding gradients when they are deep.

New-Onset Diabetes Assessment Using Artificial Intelligence-Enhanced Electrocardiography

no code implementations5 May 2022 Neil Jethani, Aahlad Puli, Hao Zhang, Leonid Garber, Lior Jankelson, Yindalon Aphinyanaphongs, Rajesh Ranganath

We found ECG-based assessment outperforms the ADA Risk test, achieving a higher area under the curve (0. 80 vs. 0. 68) and positive predictive value (13% vs. 9%) -- 2. 6 times the prevalence of diabetes in the cohort.

Quantile Filtered Imitation Learning

no code implementations2 Dec 2021 David Brandfonbrener, William F. Whitney, Rajesh Ranganath, Joan Bruna

We introduce quantile filtered imitation learning (QFIL), a novel policy improvement operator designed for offline reinforcement learning.

D4RL Imitation Learning

Inverse-Weighted Survival Games

1 code implementation NeurIPS 2021 Xintian Han, Mark Goldstein, Aahlad Puli, Thomas Wies, Adler J Perotte, Rajesh Ranganath

When the loss is proper, we show that the games always have the true failure and censoring distributions as a stationary point.

Binary Classification Survival Analysis

FastSHAP: Real-Time Shapley Value Estimation

4 code implementations ICLR 2022 Neil Jethani, Mukund Sudarshan, Ian Covert, Su-In Lee, Rajesh Ranganath

Shapley values are widely used to explain black-box models, but they are costly to calculate because they require many model evaluations.

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

no code implementations14 Jul 2021 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 images than images from the training distribution.

Out-of-Distribution Detection Out of Distribution (OOD) Detection

Out-of-distribution Generalization in the Presence of Nuisance-Induced Spurious Correlations

1 code implementation ICLR 2022 Aahlad Puli, Lily H. Zhang, Eric K. Oermann, Rajesh Ranganath

NURD finds a representation from this set that is most informative of the label under the nuisance-randomized distribution, and we prove that this representation achieves the highest performance regardless of the nuisance-label relationship.

Out-of-Distribution Generalization

Offline RL Without Off-Policy Evaluation

1 code implementation NeurIPS 2021 David Brandfonbrener, William F. Whitney, Rajesh Ranganath, Joan Bruna

In addition, we hypothesize that the strong performance of the one-step algorithm is due to a combination of favorable structure in the environment and behavior policy.

D4RL Offline RL +1

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

1 code implementation2 Mar 2021 Neil Jethani, Mukund Sudarshan, Yindalon Aphinyanaphongs, Rajesh Ranganath

While the need for interpretable machine learning has been established, many common approaches are slow, lack fidelity, or hard to evaluate.

Interpretable Machine Learning

X-CAL: Explicit Calibration for Survival Analysis

1 code implementation NeurIPS 2020 Mark Goldstein, Xintian Han, Aahlad Puli, Adler J. Perotte, Rajesh Ranganath

A survival model's calibration can be measured using, for instance, distributional calibration (D-CALIBRATION) [Haider et al., 2020] which computes the squared difference between the observed and predicted number of events within different time intervals.

Length-of-Stay prediction Survival Analysis

General Control Functions for Causal Effect Estimation from IVs

no code implementations NeurIPS 2020 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.

Deep Direct Likelihood Knockoffs

1 code implementation NeurIPS 2020 Mukund Sudarshan, Wesley Tansey, Rajesh Ranganath

Predictive modeling often uses black box machine learning methods, such as deep neural networks, to achieve state-of-the-art performance.


The Counterfactual $χ$-GAN

no code implementations9 Jan 2020 Amelia J. Averitt, Natnicha Vanitchanant, Rajesh Ranganath, Adler J. Perotte

Effect estimates, such as the average treatment effect (ATE), are then estimated as expectations under the reweighted or matched distribution, P .

Causal Inference

Energy-Inspired Models: Learning with Sampler-Induced Distributions

1 code implementation NeurIPS 2019 Dieterich Lawson, George Tucker, Bo Dai, Rajesh Ranganath

Motivated by this, we consider the sampler-induced distribution as the model of interest and maximize the likelihood of this model.

Variational Inference

GATO: Gates Are Not the Only Option

no code implementations25 Sep 2019 Mark Goldstein*, Xintian Han*, Rajesh Ranganath

GATO is constructed so that part of its hidden state does not have vanishing gradients, regardless of sequence length.

Population Predictive Checks

no code implementations2 Aug 2019 Gemma E. Moran, David M. Blei, Rajesh Ranganath

However, PPCs use the data twice -- both to calculate the posterior predictive and to evaluate it -- which can lead to overconfident assessments of the quality of a model.

General Control Functions for Causal Effect Estimation from Instrumental Variables

no code implementations8 Jul 2019 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.

Reproducibility in Machine Learning for Health

no code implementations2 Jul 2019 Matthew B. A. McDermott, Shirly Wang, Nikki Marinsek, Rajesh Ranganath, Marzyeh Ghassemi, Luca Foschini

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 outside strict human supervision.

BIG-bench Machine Learning

Adversarial Examples for Electrocardiograms

no code implementations13 May 2019 Xintian Han, Yuxuan Hu, Luca Foschini, Larry Chinitz, Lior Jankelson, Rajesh Ranganath

For this model, we utilized a new technique to generate smoothed examples to produce signals that are 1) indistinguishable to cardiologists from the original examples and 2) incorrectly classified by the neural network.

Adversarial Defense Arrhythmia Detection +1

ClinicalBERT: Modeling Clinical Notes and Predicting Hospital Readmission

2 code implementations10 Apr 2019 Kexin Huang, Jaan Altosaar, Rajesh Ranganath

Clinical notes contain information about patients that goes beyond structured data like lab values and medications.

Readmission Prediction

Kernelized Complete Conditional Stein Discrepancy

no code implementations9 Apr 2019 Raghav Singhal, Xintian Han, Saad Lahlou, Rajesh Ranganath

We introduce kernelized complete conditional Stein discrepancies (KCC-SDs).

Revisiting Auxiliary Latent Variables in Generative Models

no code implementations ICLR Workshop DeepGenStruct 2019 Dieterich Lawson, George Tucker, Bo Dai, Rajesh Ranganath

The success of enriching the variational family with auxiliary latent variables motivates applying the same techniques to the generative model.

The Random Conditional Distribution for Higher-Order Probabilistic Inference

no code implementations25 Mar 2019 Zenna Tavares, Xin Zhang, Edgar Minaysan, Javier Burroni, Rajesh Ranganath, Armando Solar Lezama

The need to condition distributional properties such as expectation, variance, and entropy arises in algorithmic fairness, model simplification, robustness and many other areas.

Fairness Probabilistic Programming

Support and Invertibility in Domain-Invariant Representations

no code implementations8 Mar 2019 Fredrik D. Johansson, David Sontag, Rajesh Ranganath

In this work, we give generalization bounds for unsupervised domain adaptation that hold for any representation function by acknowledging the cost of non-invertibility.

Generalization Bounds Unsupervised Domain Adaptation

The Variational Predictive Natural Gradient

1 code implementation7 Mar 2019 Da Tang, Rajesh Ranganath

Unlike traditional natural gradients for variational inference, this natural gradient accounts for the relationship between model parameters and variational parameters.

General Classification Variational Inference

Soft Constraints for Inference with Declarative Knowledge

no code implementations16 Jan 2019 Zenna Tavares, Javier Burroni, Edgar Minaysan, Armando Solar Lezama, Rajesh Ranganath

We develop a likelihood free inference procedure for conditioning a probabilistic model on a predicate.

Multiple Causal Inference with Latent Confounding

no code implementations21 May 2018 Rajesh Ranganath, Adler Perotte

Together, these assumptions lead to a confounder estimator regularized by mutual information.

Causal Inference

Variational Inference via \chi Upper Bound Minimization

no code implementations NeurIPS 2017 Adji Bousso Dieng, Dustin Tran, Rajesh Ranganath, John Paisley, David Blei

In this paper we propose CHIVI, a black-box variational inference algorithm that minimizes $D_{\chi}(p || q)$, the $\chi$-divergence from $p$ to $q$.

Variational Inference

Variational Sequential Monte Carlo

1 code implementation31 May 2017 Christian A. Naesseth, Scott W. Linderman, Rajesh Ranganath, David M. Blei

The success of variational approaches depends on (i) formulating a flexible parametric family of distributions, and (ii) optimizing the parameters to find the member of this family that most closely approximates the exact posterior.

Bayesian Inference Variational Inference

Proximity Variational Inference

1 code implementation24 May 2017 Jaan Altosaar, Rajesh Ranganath, David M. Blei

Consequently, PVI is less sensitive to initialization and optimization quirks and finds better local optima.

Variational Inference

Variational Inference via $χ$-Upper Bound Minimization

no code implementations1 Nov 2016 Adji B. Dieng, Dustin Tran, Rajesh Ranganath, John Paisley, David M. Blei

In this paper we propose CHIVI, a black-box variational inference algorithm that minimizes $D_{\chi}(p || q)$, the $\chi$-divergence from $p$ to $q$.

Variational Inference

Operator Variational Inference

no code implementations NeurIPS 2016 Rajesh Ranganath, Jaan Altosaar, Dustin Tran, David M. Blei

Though this divergence has been widely used, the resultant posterior approximation can suffer from undesirable statistical properties.

Bayesian Inference Variational Inference

Deep Survival Analysis

no code implementations6 Aug 2016 Rajesh Ranganath, Adler Perotte, Noémie Elhadad, David Blei

The electronic health record (EHR) provides an unprecedented opportunity to build actionable tools to support physicians at the point of care.

Survival Analysis

The Variational Gaussian Process

no code implementations20 Nov 2015 Dustin Tran, Rajesh Ranganath, David M. Blei

Variational inference is a powerful tool for approximate inference, and it has been recently applied for representation learning with deep generative models.

Representation Learning Variational Inference

Hierarchical Variational Models

1 code implementation7 Nov 2015 Rajesh Ranganath, Dustin Tran, David M. Blei

We study HVMs on a variety of deep discrete latent variable models.

Variational Inference

Dynamic Poisson Factorization

no code implementations15 Sep 2015 Laurent Charlin, Rajesh Ranganath, James McInerney, David M. Blei

Models for recommender systems use latent factors to explain the preferences and behaviors of users with respect to a set of items (e. g., movies, books, academic papers).

Recommendation Systems Variational Inference

Correlated Random Measures

no code implementations2 Jul 2015 Rajesh Ranganath, David Blei

We develop correlated random measures, random measures where the atom weights can exhibit a flexible pattern of dependence, and use them to develop powerful hierarchical Bayesian nonparametric models.

Variational Inference

Deep Exponential Families

no code implementations10 Nov 2014 Rajesh Ranganath, Linpeng Tang, Laurent Charlin, David M. Blei

We describe \textit{deep exponential families} (DEFs), a class of latent variable models that are inspired by the hidden structures used in deep neural networks.

Variational Inference

Variational Tempering

no code implementations7 Nov 2014 Stephan Mandt, James McInerney, Farhan Abrol, Rajesh Ranganath, David Blei

Lastly, we develop local variational tempering, which assigns a latent temperature to each data point; this allows for dynamic annealing that varies across data.

Variational Inference

Black Box Variational Inference

2 code implementations31 Dec 2013 Rajesh Ranganath, Sean Gerrish, David M. Blei

We evaluate our method against the corresponding black box sampling based methods.

Stochastic Optimization Variational Inference

Cannot find the paper you are looking for? You can Submit a new open access paper.