Soumya Ghosh

I am a Research Staff Member at IBM Research. My research focuses on the design of flexible statistical models and efficient inference algorithms for reasoning about noisy, high-dimensional data. My recent work has examined approaches for combining the complementary strengths of Bayesian methods, graphical models, and deep neural networks for modeling the progression of neurodegenerative diseases and procedures for assessing the sensitivity and robustness of inferences drawn from such statistical methods.