Search Results for author: Soumya Ghosh

Found 22 papers, 11 papers with code

Post-hoc loss-calibration for Bayesian neural networks

no code implementations13 Jun 2021 Meet P. Vadera, Soumya Ghosh, Kenney Ng, Benjamin M. Marlin

Bayesian decision theory provides an elegant framework for acting optimally under uncertainty when tractable posterior distributions are available.

Decision Making

Measuring the robustness of Gaussian processes to kernel choice

no code implementations11 Jun 2021 William T. Stephenson, Soumya Ghosh, Tin D. Nguyen, Mikhail Yurochkin, Sameer K. Deshpande, Tamara Broderick

We demonstrate in both synthetic and real-world examples that decisions made with a GP can exhibit non-robustness to kernel choice, even when prior draws are qualitatively interchangeable to a user.

Gaussian Processes

Uncertainty Quantification 360: A Holistic Toolkit for Quantifying and Communicating the Uncertainty of AI

1 code implementation2 Jun 2021 Soumya Ghosh, Q. Vera Liao, Karthikeyan Natesan Ramamurthy, Jiri Navratil, Prasanna Sattigeri, Kush R. Varshney, Yunfeng Zhang

In this paper, we describe an open source Python toolkit named Uncertainty Quantification 360 (UQ360) for the uncertainty quantification of AI models.

Fairness

Uncertainty Characteristics Curves: A Systematic Assessment of Prediction Intervals

1 code implementation1 Jun 2021 Jiri Navratil, Benjamin Elder, Matthew Arnold, Soumya Ghosh, Prasanna Sattigeri

Accurate quantification of model uncertainty has long been recognized as a fundamental requirement for trusted AI.

Prediction Intervals

EVA: Generating Longitudinal Electronic Health Records Using Conditional Variational Autoencoders

no code implementations18 Dec 2020 Siddharth Biswal, Soumya Ghosh, Jon Duke, Bradley Malin, Walter Stewart, Jimeng Sun

De-identified EHRs do not adequately address the needs of health systems, as de-identified data are susceptible to re-identification and its volume is also limited.

Variational Inference

Model Fusion with Kullback--Leibler Divergence

1 code implementation ICML 2020 Sebastian Claici, Mikhail Yurochkin, Soumya Ghosh, Justin Solomon

Our algorithm relies on a mean field assumption for both the fused model and the individual dataset posteriors and proceeds using a simple assign-and-average approach.

Federated Learning

Approximate Cross-Validation for Structured Models

1 code implementation NeurIPS 2020 Soumya Ghosh, William T. Stephenson, Tin D. Nguyen, Sameer K. Deshpande, Tamara Broderick

But this existing ACV work is restricted to simpler models by the assumptions that (i) data across CV folds are independent and (ii) an exact initial model fit is available.

Isolating Latent Structure with Cross-population Variational Autoencoders

no code implementations25 Sep 2019 Joe Davison, Kristen A. Severson, Soumya Ghosh

A significant body of recent work has examined variational autoencoders as a powerful approach for tasks which involve modeling the distribution of complex data such as images and text.

Continual Learning Image Denoising

Bayesian Nonparametric Federated Learning of Neural Networks

1 code implementation28 May 2019 Mikhail Yurochkin, Mayank Agarwal, Soumya Ghosh, Kristjan Greenewald, Trong Nghia Hoang, Yasaman Khazaeni

In federated learning problems, data is scattered across different servers and exchanging or pooling it is often impractical or prohibited.

Federated Learning General Classification +1

Probabilistic Federated Neural Matching

no code implementations ICLR 2019 Mikhail Yurochkin, Mayank Agarwal, Soumya Ghosh, Kristjan Greenewald, Nghia Hoang, Yasaman Khazaeni

In federated learning problems, data is scattered across different servers and exchanging or pooling it is often impractical or prohibited.

Federated Learning General Classification +1

DPVis: Visual Analytics with Hidden Markov Models for Disease Progression Pathways

no code implementations26 Apr 2019 Bum Chul Kwon, Vibha Anand, Kristen A Severson, Soumya Ghosh, Zhaonan Sun, Brigitte I Frohnert, Markus Lundgren, Kenney Ng

Clinical researchers use disease progression models to understand patient status and characterize progression patterns from longitudinal health records.

Projected BNNs: Avoiding weight-space pathologies by learning latent representations of neural network weights

no code implementations16 Nov 2018 Melanie F. Pradier, Weiwei Pan, Jiayu Yao, Soumya Ghosh, Finale Doshi-Velez

As machine learning systems get widely adopted for high-stake decisions, quantifying uncertainty over predictions becomes crucial.

Variational Inference

Unsupervised learning with contrastive latent variable models

1 code implementation14 Nov 2018 Kristen Severson, Soumya Ghosh, Kenney Ng

Here, we present a probabilistic model for dimensionality reduction to discover signal that is enriched in the target dataset relative to the background dataset.

Dimensionality Reduction Frame

Structured Variational Learning of Bayesian Neural Networks with Horseshoe Priors

1 code implementation ICML 2018 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.

Model Selection reinforcement-learning

Simultaneous Modeling of Multiple Complications for Risk Profiling in Diabetes Care

no code implementations19 Feb 2018 Bin Liu, Ying Li, Soumya Ghosh, Zhaonan Sun, Kenney Ng, Jianying Hu

The proposed method is favorable for healthcare applications because in additional to improved prediction performance, relationships among the different risks and risk factors are also identified.

Multi-Task Learning

Personalizing Gesture Recognition Using Hierarchical Bayesian Neural Networks

no code implementations CVPR 2017 Ajjen Joshi, Soumya Ghosh, Margrit Betke, Stan Sclaroff, Hanspeter Pfister

Leveraging recent work on learning Bayesian neural networks, we build fast, scalable algorithms for inferring the posterior distribution over all network weights in the hierarchy.

Active Learning Gesture Recognition

Model Selection in Bayesian Neural Networks via Horseshoe Priors

1 code implementation29 May 2017 Soumya Ghosh, Finale Doshi-Velez

Bayesian Neural Networks (BNNs) have recently received increasing attention for their ability to provide well-calibrated posterior uncertainties.

Model Selection

From Deformations to Parts: Motion-based Segmentation of 3D Objects

2 code implementations NeurIPS 2012 Soumya Ghosh, Matthew Loper, Erik B. Sudderth, Michael J. Black

We develop a method for discovering the parts of an articulated object from aligned meshes capturing various three-dimensional (3D) poses.

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