About
 

Soumya Ghosh

Research Staff Member

Twitter LinkedIn Google Scholar

Who they work with

Categories

AI in Healthcare Bayesian Modeling Deep Learning

I am a research scientist at IBM Research, Cambridge and the MIT-IBM Watson AI lab. I work on developing statistical models for understanding and explaining images, text, and noisy, real world healthcare data.I hold a Ph.D. in Computer Science from Brown University, where I was advised by Erik Sudderth. Before Brown, I spent a few years in beautiful Boulder getting a master’s degree from the University of Colorado. At Colorado, I was advised by Jane Mulligan. Going further back, I went to the University of Mumbai (Bombay) (KJSCE) as an undergrad. I also spent a year as a postdoctoral scientist at the now defunct Disney research, Cambridge.

Recent Highlights

  • A comprehensive overview of learning Bayesian neural networks with Horseshoe priors will appear in JMLR.
  • New code release for distance dependent Chinese restaurant processes. The code by Ishana Shastri is an efficient, python translated, version of this old MATLAB package.
  • Our Work on using Bayesian non-parametric meta models for fusing local models will appear at NeurIPS 2019.
  • Commonly used metrics such as test log likelihoods can be misleading indicators of posterior quality of BNNs. Preliminary work will appear at Uncertainty and Robustness workshop at ICML’ 19.

Top Work

SPAHM: Parameter matching for model fusion

SPAHM: Parameter matching for model fusion

Bayesian Modeling

Publications with the MIT-IBM Watson AI Lab

Post-hoc Uncertainty Learning using a Dirichlet Meta-Model
Post-hoc Uncertainty Learning using a Dirichlet Meta-Model
AAAI
 
Fair Infinitesimal Jackknife: Mitigating the Influence of Biased Training Data Points Without Refitting
Fair Infinitesimal Jackknife: Mitigating the Influence of Biased Training Data Points Without Refitting
NeurIPS
 
Measuring the robustness of Gaussian processes to kernel choice
Measuring the robustness of Gaussian processes to kernel choice
AISTATS
 
Model Fusion with Kullback–Leibler Divergence
Model Fusion with Kullback–Leibler Divergence
ICML
 
Approximate Cross-Validation for Structured Models
Approximate Cross-Validation for Structured Models
NeurIPS
 
Statistical Model Aggregation via Parameter Matching
Statistical Model Aggregation via Parameter Matching
NeurIPS
 
SPAHM: Parameter matching for model fusion
SPAHM: Parameter matching for model fusion
Bayesian Modeling
 
Bayesian Nonparametric Federated Learning of Neural Networks
Bayesian Nonparametric Federated Learning of Neural Networks
Federated Learning
 
Unsupervised learning with contrastive latent variable models
Unsupervised learning with contrastive latent variable models
Unsupervised Learning