Shreyas Padhy
Email: shreyaspadhy(at)

I am an AI Resident in the Google Brain team at Cambridge, MA. My research interests lie in calibration and uncertainty estimation in machine learning, Bayesian methods and applications in biomedicine. At Google Brain, I work with Jasper Snoek and Balaji Lakshminarayanan on probabilistic machine learning methods that are well calibrated and generalize well.

Previously, I received my Masters in Biomedical Engineering from Johns Hopkins University, where I worked with Dr, Michael I. Miller on using machine learning and computational anatomy to understand the pathology of neurodegenerative diseases such as Alzheimers and schizophrenia using diffeomorphic mapping of brain MRI scans.

I was an undergraduate in Engineering Physics at IIT Delhi, where I worked with Dr. Uday Khankhoje on stochastic solutions to forward and inverse imaging. I spent a summer at the Center for Medical Image Computing working with Dr. Simon Arridge on inverse problems in computational tomography.

Recent Updates

22 October 2020: Our work on developing Spectral-Normalized Gaussian Proces (SNGP) was accepted at NeurIPS 2020 for poster presentation. [code] [preprint]

30 July 2020: We have open-sourced Uncertainty Metrics, a Python library to provide an easy-to-use interface for computing various uncertainty and calibration metrics. [code]

16 July 2020: We released Uncertainty Baselines, a Python and Tensorflow library that provides templates and high-quality implementations of standard and state-of-the-art uncertainty methods. [code]

10 July 2020: Our work analyzing loss functions for calibration and OOD robustness was accepted as a poster at the Uncertainty & Robustness in Deep Learning Workshop at ICML 2020. [code] [paper]

10 July 2020: Our work analyzing the effects of batch normalization on the calibration properties of neural nets was accepted as a poster at the Uncertainty & Robustness in Deep Learning Workshop at ICML 2020. [code] [paper]

1 August 2018: Attended the NeuroHackademy Summer School at UWashington, and created EasyHCP, an open-source software package for easy and efficient querying of data from the Human Connectome Project using AWS Buckets and Boto. [code]


Simple and principled uncertainty estimation with deterministic deep learning via distance awareness
Jeremiah Zhe Liu, Zi Lin, Shreyas Padhy, Dustin Tran, Tania Bedrax-Weiss, and Balaji Lakshminarayanan.
Advances in Neural Information Processing Systems 2020.
[code] [preprint]


Using deep Siamese neural networks for detection of brain asymmetries associated with Alzheimer's Disease and Mild Cognitive Impairment
C.F. Liu*, Shreyas Padhy*, S. Ramachandran, V.X. Wang, A. Efimov, A. Bernal, L. Shi, M. Vaillant, J.T Ratnanather, A.V Faria, B. Caffo, M. Albert, M.I Miller.
Magnetic resonance imaging 64 (2019): 190-199., 2019.

Stochastic Solutions to Rough Surface Scattering using the finite element method
Uday K. Khankhoje, Shreyas Padhy.
IEEE Transactions on Antennas and Propagation, (Vol 65, No 08), 2017.
[website] [paper]


Revisiting One-vs-All Classifiers for Predictive Uncertainty and Out-of-Distribution Detection in Neural Networks
Shreyas Padhy, Zachary Nado, Jie Ren, Jeremiah Liu, Jasper Snoek, and Balaji Lakshminarayanan.
ICML 2020 Workshop on Uncertainty and Robustness in Deep Learning.
[code] [paper]

“Evaluating prediction-time batch normalization for robustness under covariate shift
Zachary Nado, Shreyas Padhy, D. Sculley, Alexander D'Amour, Balaji Lakshminarayanan, and Jasper Snoek.
ICML 2020 Workshop on Uncertainty and Robustness in Deep Learning.
[code] [paper]

Graduate Thesis

“Analyzing shape and residual pose of subcortical structures in brains of subjects with schizophrenia
Shreyas Padhy
Masters Thesis, Master of Science in Engineering, Department of Biomedical Engineering, Johns Hopkins University.

Template: Everyone here, but specifically this version