147 citations · 448 across the 18 of their papers we have counts for
19 papers
Reliable Gradient-free and Likelihood-free Prompt Tuning
Maohao Shen, Soumya Ghosh, Prasanna Sattigeri +3
Due to privacy or commercial constraints, large pre-trained language models (PLMs) are often offered as black-box APIs. Fine-tuning such models to downstream tasks is challenging b…
Post-hoc Uncertainty Learning using a Dirichlet Meta-Model
Maohao Shen, Yuheng Bu, Prasanna Sattigeri +3
It is known that neural networks have the problem of being over-confident when directly using the output label distribution to generate uncertainty measures. Existing methods mainl…
Fair Infinitesimal Jackknife: Mitigating the Influence of Biased Training Data Points Without Refitting
Prasanna Sattigeri, Soumya Ghosh, Inkit Padhi +2
In consequential decision-making applications, mitigating unwanted biases in machine learning models that yield systematic disadvantage to members of groups delineated by sensitive…
Post-hoc loss-calibration for Bayesian neural networks
Meet P. Vadera, Soumya Ghosh, Kenney Ng +1
Bayesian decision theory provides an elegant framework for acting optimally under uncertainty when tractable posterior distributions are available. Modern Bayesian models, however,…
Uncertainty Quantification 360: A Holistic Toolkit for Quantifying and Communicating the Uncertainty of AI
Soumya Ghosh, Q. Vera Liao, Karthikeyan Natesan Ramamurthy +4
In this paper, we describe an open source Python toolkit named Uncertainty Quantification 360 (UQ360) for the uncertainty quantification of AI models. The goal of this toolkit is t…
Measuring the robustness of Gaussian processes to kernel choice
William T. Stephenson, Soumya Ghosh, Tin D. Nguyen +3
Gaussian processes (GPs) are used to make medical and scientific decisions, including in cardiac care and monitoring of atmospheric carbon dioxide levels. Notably, the choice of GP…
Uncertainty Characteristics Curves: A Systematic Assessment of Prediction Intervals
Jiri Navratil, Benjamin Elder, Matthew Arnold +2
Accurate quantification of model uncertainty has long been recognized as a fundamental requirement for trusted AI. In regression tasks, uncertainty is typically quantified using pr…
EVA: Generating Longitudinal Electronic Health Records Using Conditional Variational Autoencoders
Siddharth Biswal, Soumya Ghosh, Jon Duke +3
Researchers require timely access to real-world longitudinal electronic health records (EHR) to develop, test, validate, and implement machine learning solutions that improve the q…
Model Fusion with Kullback--Leibler Divergence
Sebastian Claici, Mikhail Yurochkin, Soumya Ghosh +1
We propose a method to fuse posterior distributions learned from heterogeneous datasets. Our algorithm relies on a mean field assumption for both the fused model and the individual…
Approximate Cross-Validation for Structured Models
Soumya Ghosh, William T. Stephenson, Tin D. Nguyen +2
Many modern data analyses benefit from explicitly modeling dependence structure in data -- such as measurements across time or space, ordered words in a sentence, or genes in a gen…
Statistical Model Aggregation via Parameter Matching
Mikhail Yurochkin, Mayank Agarwal, Soumya Ghosh +2
We consider the problem of aggregating models learned from sequestered, possibly heterogeneous datasets. Exploiting tools from Bayesian nonparametrics, we develop a general meta-mo…
Quality of Uncertainty Quantification for Bayesian Neural Network Inference
Jiayu Yao, Weiwei Pan, Soumya Ghosh +1
Bayesian Neural Networks (BNNs) place priors over the parameters in a neural network. Inference in BNNs, however, is difficult; all inference methods for BNNs are approximate. In t…
Bayesian Nonparametric Federated Learning of Neural Networks
Mikhail Yurochkin, Mayank Agarwal, Soumya Ghosh +3
In federated learning problems, data is scattered across different servers and exchanging or pooling it is often impractical or prohibited. We develop a Bayesian nonparametric fram…
DPVis: Visual Analytics with Hidden Markov Models for Disease Progression Pathways
Bum Chul Kwon, Vibha Anand, Kristen A Severson +5
Clinical researchers use disease progression models to understand patient status and characterize progression patterns from longitudinal health records. One approach for disease pr…
Unsupervised learning with contrastive latent variable models
Kristen Severson, Soumya Ghosh, Kenney Ng
In unsupervised learning, dimensionality reduction is an important tool for data exploration and visualization. Because these aims are typically open-ended, it can be useful to fra…
Projected BNNs: Avoiding weight-space pathologies by learning latent representations of neural network weights
Melanie F. Pradier, Weiwei Pan, Jiayu Yao +2
As machine learning systems get widely adopted for high-stake decisions, quantifying uncertainty over predictions becomes crucial. While modern neural networks are making remarkabl…
Structured Variational Learning of Bayesian Neural Networks with Horseshoe Priors
Soumya Ghosh, Jiayu Yao, Finale Doshi-Velez
Bayesian Neural Networks (BNNs) have recently received increasing attention for their ability to provide well-calibrated posterior uncertainties. However, model selection---even ch…
Simultaneous Modeling of Multiple Complications for Risk Profiling in Diabetes Care
Bin Liu, Ying Li, Soumya Ghosh +3
Type 2 diabetes mellitus (T2DM) is a chronic disease that often results in multiple complications. Risk prediction and profiling of T2DM complications is critical for healthcare pr…
Model Selection in Bayesian Neural Networks via Horseshoe Priors
Soumya Ghosh, Finale Doshi-Velez
Bayesian Neural Networks (BNNs) have recently received increasing attention for their ability to provide well-calibrated posterior uncertainties. However, model selection---even ch…