Shreyas Padhy
Email: sp2058 (at)

I am a PhD student in the Machine Learning Group at the University of Cambridge, supervised by Dr. Jośe Miguel Hernández-Lobato. My research interests lie in massively scalable Bayesian inference and probabilistic machine learning, uncertainty estimation and out-of-distribution detection, and diffusion models and sampling.

Previously, I was an AI Resident in the Google Brain team at Cambridge, MA, where I worked with Jasper Snoek and Balaji Lakshminarayanan on probabilistic machine learning methods.

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 received my Bachelors in Engineering Physics at IIT Delhi, where I worked with Dr. Uday Khankhoje on stochastic solutions to forward and inverse imaging.

Recent Updates

December 2023: I gave an invited talk at the NeurIPS@Cambridge meetup on our NeurIPS Oral [event] [paper]

November 2023: We have a new preprint on annealed importance sampling with constrained diffusions with SOTA results on log-partition estimation [paper]

October 2023: We improve SGD-based sampling from GPs even further in a new preprint [paper]

October 2023: I gave an invited talk at Microsoft Research Cambridge on our NeurIPS Oral [paper]

September 2023: Our paper on scaling Gaussian Processes to millions of datapoints using SGD has been accepted as an Oral at NeurIPS 2023! [code] [paper]

July 2023: I gave a talk on SDEs and Schrodinger Bridges at the Cambridge Machine Learning Reading Group. [slides]

May 2023: I will be a research intern in the Project Alexandria team in Microsoft Research Cambridge!

January 2023: Our paper on scaling linearised Laplace to a very large scale (ResNet models on CIFAR-100) has been accepted to ICLR 2023! [code] [paper]

January 2023: Our follow-up paper on Spectral-Normalized Gaussian Process (SNGP) has been accepted to JMLR 2023! [code] [paper]


Sampling from Gaussian Process Posteriors using Stochastic Gradient Descent
Shreyas Padhy*, Jihao Andreas Lin*, Javier Antorán*, David Janz, José Miguel Hernández-Lobato, Alexander Terenin.
NeurIPS 2023 (Oral) [code] [paper]

Sampling-based inference for large linear models, with application to linearised Laplace
Shreyas Padhy*, Javier Antorán*, Riccardo Barbano, Eric Nalisnick, David Janz, José Miguel Hernández-Lobato
ICLR 2023 [code] [paper] [slides] [poster]

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.
NeurIPS 2020 [code] [paper]


Transport meets Variational Inference: Controlled Monte Carlo Diffusions
Francisco Vargas*, Shreyas Padhy*, Denis Blessing, Nikolas Nüsken.

Stochastic Gradient Descent for Gaussian Processes Done Right
Shreyas Padhy*, Jihao Andreas Lin*, Javier Antorán*, Austin Tripp, Alexander Terenin, Csaba Szepesvári, José Miguel Hernández-Lobato, David Janz

Kernel Regression with Infinite-Width Neural Networks on Millions of Examples
Ben Adlam, Jaehoon Lee, Shreyas Padhy, Zachary Nado, Jasper Snoek.


A Simple Approach to Improve Single-Model Deep Uncertainty via Distance-Awareness
Jeremiah Zhe Liu*, Shreyas Padhy*, Jie Ren*, Zi Lin, Yeming Wen, Ghassen Jerfel, Zack Nado, Jasper Snoek, Dustin Tran, Balaji Lakshminarayanan
JMLR 2023 [code] [paper] [poster]

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]

A Simple Fix to Mahalanobis Distance for Improving Near-OOD Detection
Jie Ren, Stanislav Fort, Jeremiah Liu, Abhijit Guha Roy, Shreyas Padhy, and Balaji Lakshminarayanan
ICML 2021 Workshop on Uncertainty and Robustness in Deep Learning.

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]

Uncertainty Baselines: Benchmarks for Uncertainty & Robustness in Deep Learning
Zachary Nado at al.
Bayesian Deep Learning Workshop, 2021.
[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